Remote Sensing Applications-Society and Environment最新文献_第4页

Spatiotemporal dynamics of carbon, water, and energy balance in Bangladesh using multi-source remote sensing and climate data 基于多源遥感和气候数据的孟加拉国碳、水和能量平衡时空动态

IF 4.5 Q2 ENVIRONMENTAL SCIENCES

Remote Sensing Applications-Society and Environment

Pub Date : 2026-01-01 DOI: 10.1016/j.rsase.2025.101847

Nur Hussain , Md Saifuzzaman , Didar Islam , S.M. Shahriar Ahmed , Md Shamim Ahamed , Dara Shamsuddin

Exploring the complex interactions between climate variables and ecosystem processes is crucial for understanding long-term environmental changes. This study examines the spatiotemporal dynamics of carbon, water and energy fluxes and their impacts on ecosystem processes in Bangladesh from 2005 to 2022 utilizing multi-source remote sensing and ground-based meteorological data. Carbon dynamics are estimated through gross primary productivity (GPP), net primary production (NPP), and ecosystem respiration (RE). Water and energy balances are derived from evapotranspiration (ET), water use efficiency (WUE), net radiation (Rn), and latent heat (LE). Our estimates indicate that GPP varied from 2351.29 g C m⁻² y⁻¹ in 2009–2178.45 g C m⁻² y⁻¹ in 2020, while NPP ranged from 1248.13 g C m⁻² y⁻¹ in 2012 to 929.46 g C m⁻² y⁻¹ in 2020, reflecting temporal variations in photosynthetic efficiency and carbon storage. The ratio of LE/Rn was found to vary from 0.72 to 1.01, with an average of 83 %, indicating that a significant portion of the radiative energy was transferred to the atmosphere as turbulent flux. Validation of LUE-based GPP compared to FLUXCOM-GPP showed a moderate correlation (R² = 0.61, p < 0.005), supporting the reliability of the estimates. We also conducted multivariate regression analysis to assess the relationships between climate variables and carbon, water, and energy balance. The results indicate that photosynthetically active radiation (PAR) is the primary and dominant driver of GPP (R² = 0.97), while temperature and precipitation are key factors significantly influencing carbon uptake. This study presents a comprehensive, integrated assessment of carbon, water, and energy fluxes at the national scale across Bangladesh, emphasizing the crucial role of climate variables in shaping these fluxes and offering valuable insights for climate-resilient land management and sustainable carbon strategies in monsoon-dominated regions.

探索气候变量和生态系统过程之间复杂的相互作用对于理解长期环境变化至关重要。本研究利用多源遥感和地面气象数据，研究了2005 - 2022年孟加拉国碳、水和能量通量的时空动态及其对生态系统过程的影响。碳动态通过总初级生产力（GPP）、净初级生产力（NPP）和生态系统呼吸（RE）来估算。水分和能量平衡来源于蒸散发（ET）、水分利用效率（WUE）、净辐射（Rn）和潜热（LE）。我们的估计表明，GPP在2009年至2020年的2351.29 g C m−2 y−1之间变化，而NPP在2012年的1248.13 g C m−2 y−1到2020年的929.46 g C m−2 y−1之间变化，反映了光合效率和碳储量的时间变化。LE/Rn的比值在0.72 ~ 1.01之间变化，平均为83%，表明有很大一部分辐射能量以湍流通量的形式转移到大气中。与FLUXCOM-GPP相比，基于lue的GPP验证显示有中等相关性（R2 = 0.61, p < 0.005），支持估计的可靠性。我们还进行了多变量回归分析，以评估气候变量与碳、水和能量平衡之间的关系。结果表明，光合有效辐射（PAR）是GPP的主要和主导驱动因子（R2 = 0.97），而温度和降水是影响碳吸收的关键因素。本研究对孟加拉国全国范围内的碳、水和能源通量进行了全面、综合的评估，强调了气候变量在形成这些通量方面的关键作用，并为季风主导地区的气候适应型土地管理和可持续碳战略提供了有价值的见解。

{"title":"Spatiotemporal dynamics of carbon, water, and energy balance in Bangladesh using multi-source remote sensing and climate data","authors":"Nur Hussain , Md Saifuzzaman , Didar Islam , S.M. Shahriar Ahmed , Md Shamim Ahamed , Dara Shamsuddin","doi":"10.1016/j.rsase.2025.101847","DOIUrl":"10.1016/j.rsase.2025.101847","url":null,"abstract":"<div><div>Exploring the complex interactions between climate variables and ecosystem processes is crucial for understanding long-term environmental changes. This study examines the spatiotemporal dynamics of carbon, water and energy fluxes and their impacts on ecosystem processes in Bangladesh from 2005 to 2022 utilizing multi-source remote sensing and ground-based meteorological data. Carbon dynamics are estimated through gross primary productivity (GPP), net primary production (NPP), and ecosystem respiration (RE). Water and energy balances are derived from evapotranspiration (ET), water use efficiency (WUE), net radiation (Rn), and latent heat (LE). Our estimates indicate that GPP varied from 2351.29 g C m<sup>−2</sup> y<sup>−1</sup> in 2009–2178.45 g C m<sup>−2</sup> y<sup>−1</sup> in 2020, while NPP ranged from 1248.13 g C m<sup>−2</sup> y<sup>−1</sup> in 2012 to 929.46 g C m<sup>−2</sup> y<sup>−1</sup> in 2020, reflecting temporal variations in photosynthetic efficiency and carbon storage. The ratio of LE/Rn was found to vary from 0.72 to 1.01, with an average of 83 %, indicating that a significant portion of the radiative energy was transferred to the atmosphere as turbulent flux. Validation of LUE-based GPP compared to FLUXCOM-GPP showed a moderate correlation (R<sup>2</sup> = 0.61, p < 0.005), supporting the reliability of the estimates. We also conducted multivariate regression analysis to assess the relationships between climate variables and carbon, water, and energy balance. The results indicate that photosynthetically active radiation (PAR) is the primary and dominant driver of GPP (R<sup>2</sup> = 0.97), while temperature and precipitation are key factors significantly influencing carbon uptake. This study presents a comprehensive, integrated assessment of carbon, water, and energy fluxes at the national scale across Bangladesh, emphasizing the crucial role of climate variables in shaping these fluxes and offering valuable insights for climate-resilient land management and sustainable carbon strategies in monsoon-dominated regions.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"41 ","pages":"Article 101847"},"PeriodicalIF":4.5,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145884536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Monitoring of the smouldering coal-waste dump in Chorzów (Poland) using spectral indices: A UAV- and satellite-based approach 使用光谱指数监测Chorzów（波兰）的闷烧煤矸石堆：基于无人机和卫星的方法

IF 4.5 Q2 ENVIRONMENTAL SCIENCES

Remote Sensing Applications-Society and Environment

Pub Date : 2026-01-01 DOI: 10.1016/j.rsase.2025.101865

Anna Abramowicz, Michał Laska, Ádám Nádudvari, Oimahmad Rahmonov

The study aimed to evaluate the applicability of environmental indices in the monitoring of smouldering coal-waste dumps. A dump located in the Upper Silesian Coal Basin served as the research site for a multi-method analysis combining remote sensing and field-based data. Two UAV survey campaigns were conducted, capturing RGB, infrared, and multispectral imagery. These were supplemented with direct ground measurements of subsurface temperature and detailed vegetation mapping. Additionally, publicly available satellite data from the Landsat and Sentinel missions were analysed. A range of vegetation and fire-related indices (NDVI, SAVI, EVI, BAI, among others) were calculated to identify thermally active zones and assess vegetation conditions within these degraded areas. The results revealed strong seasonal variability in vegetation indices on thermally active sites, with evidence of disrupted vegetation cycles, including winter greening in moderately heated root zones – a pattern indicative of stress and degradation processes. While open-access satellite data, such as Landsat and Sentinel-2, proved useful in reconstructing the fire history of the dump, their spatial resolution was insufficient for detailed monitoring of small-scale thermal anomalies. The study highlights the diagnostic potential of UAV-based remote sensing in post-industrial environments undergoing land degradation but emphasises the importance of field validation for accurate environmental assessment.

本研究旨在评价环境指标在阴燃煤矸石堆场监测中的适用性。位于上西里西亚煤盆地的一个垃圾场作为研究地点，进行了结合遥感和实地数据的多方法分析。进行了两次无人机调查运动，捕获RGB、红外和多光谱图像。这些数据还补充了地下温度的直接地面测量和详细的植被测绘。此外，还分析了陆地卫星和哨兵任务的公开卫星数据。计算了一系列植被和火灾相关指数（NDVI、SAVI、EVI、BAI等），以确定热活跃区并评估这些退化地区的植被状况。结果显示，在热活跃区，植被指数具有强烈的季节性变化，植被循环被破坏，包括在中等热的根区冬季绿化，这是一种指示应力和退化过程的模式。虽然开放获取的卫星数据，如Landsat和Sentinel-2，在重建垃圾场的火灾历史方面被证明是有用的，但它们的空间分辨率不足以详细监测小规模的热异常。该研究强调了基于无人机的遥感在经历土地退化的后工业环境中的诊断潜力，但强调了实地验证对准确环境评估的重要性。

{"title":"Monitoring of the smouldering coal-waste dump in Chorzów (Poland) using spectral indices: A UAV- and satellite-based approach","authors":"Anna Abramowicz, Michał Laska, Ádám Nádudvari, Oimahmad Rahmonov","doi":"10.1016/j.rsase.2025.101865","DOIUrl":"10.1016/j.rsase.2025.101865","url":null,"abstract":"<div><div>The study aimed to evaluate the applicability of environmental indices in the monitoring of smouldering coal-waste dumps. A dump located in the Upper Silesian Coal Basin served as the research site for a multi-method analysis combining remote sensing and field-based data. Two UAV survey campaigns were conducted, capturing RGB, infrared, and multispectral imagery. These were supplemented with direct ground measurements of subsurface temperature and detailed vegetation mapping. Additionally, publicly available satellite data from the Landsat and Sentinel missions were analysed. A range of vegetation and fire-related indices (NDVI, SAVI, EVI, BAI, among others) were calculated to identify thermally active zones and assess vegetation conditions within these degraded areas. The results revealed strong seasonal variability in vegetation indices on thermally active sites, with evidence of disrupted vegetation cycles, including winter greening in moderately heated root zones – a pattern indicative of stress and degradation processes. While open-access satellite data, such as Landsat and Sentinel-2, proved useful in reconstructing the fire history of the dump, their spatial resolution was insufficient for detailed monitoring of small-scale thermal anomalies. The study highlights the diagnostic potential of UAV-based remote sensing in post-industrial environments undergoing land degradation but emphasises the importance of field validation for accurate environmental assessment.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"41 ","pages":"Article 101865"},"PeriodicalIF":4.5,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145926023","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Precise 3D crustal displacement retrieval in GCP-free environments: A geodetic and deep learning–assisted integration of InSAR and optical stereo data near the Denali Fault 无gcp环境下精确三维地壳位移反演：迪纳里断裂带附近InSAR和光学立体数据的大地测量和深度学习辅助整合

IF 4.5 Q2 ENVIRONMENTAL SCIENCES

Remote Sensing Applications-Society and Environment

Pub Date : 2026-01-01 DOI: 10.1016/j.rsase.2026.101894

Zahra Alizadeh Zakaria , Farshid Farnood Ahmadi , Hamid Ebadi

Retrieving accurate 3D deformation fields from Interferometric Synthetic Aperture Radar)InSAR(line-of-sight (LOS) measurements is challenging because LOS data provide only one-dimensional motion, and the absence of ground control points (GCPs) in remote regions makes reliable 3D reconstruction even more difficult. This study introduces a deep learning-assisted approach to map 3D deformation fields without GCPs, integrating Pleiades stereo imagery with InSAR techniques over a 20 km × 20 km segment of the Denali Fault, Alaska. Initial 3D displacements from Pleiades, derived through DEM differencing and COSI-Corr, eliminate GCPs and reveal vertical displacements of ±10 mm (uplift/subsidence), with horizontal displacements of ±6.4 mm (east-west) and ±5.9 mm (north-south), consistent with the fault's right-lateral strike-slip kinematics and local GNSS IGS14/NNR velocities (2019–2024). These Pleiades displacements, combined with PS-InSAR rates and geological features like slope and Terrain Ruggedness Index (TRI), serve as inputs to a U-Net model that transforms LOS data into 3D fields, expanding displacement ranges to ±20 mm across all components. We enhance U-Net estimates with geodetic optimization and use Monte Carlo Dropout (10 samples) to quantify uncertainties of 0.1–0.3 mm for east-west and 0.5–0.8 mm for north-south and vertical displacements. Validation of the model against Pleiades test data yields RMSEs of 1.17 mm (east-west), 1.46 mm (north-south), and 1.52 mm (vertical), with an RMSE of 1.98 mm against the vertical component of three local GNSS stations (6–50 km distance, IGS14/NNR frame, 2019–2024). This InSAR-Pleiades-deep learning method offers a scalable solution for 3D deformation monitoring, advancing seismic hazard assessment in GCP-free environments.

从干涉合成孔径雷达（InSAR）视距（LOS）测量中获取准确的3D变形场是具有挑战性的，因为LOS数据仅提供一维运动，并且在偏远地区缺乏地面控制点（gcp），使得可靠的3D重建变得更加困难。该研究引入了一种深度学习辅助方法来绘制没有gcp的3D变形场，将Pleiades立体图像与InSAR技术集成在阿拉斯加Denali断层的20公里× 20公里段上。Pleiades的初始三维位移通过DEM差分和cos - corr得到，消除了gcp，显示垂直位移为±10 mm（隆起/沉降），水平位移为±6.4 mm（东西方向）和±5.9 mm（南北方向），与断层的右侧走滑运动学和当地GNSS IGS14/NNR速度（2019-2024）一致。这些Pleiades位移，结合PS-InSAR速率和地质特征（如坡度和地形崎岖指数（TRI）），作为U-Net模型的输入，将LOS数据转换为3D场，将所有组件的位移范围扩展到±20毫米。我们通过大地测量优化来增强U-Net估计，并使用蒙特卡罗Dropout（10个样本）来量化东西位移0.1-0.3 mm，南北和垂直位移0.5-0.8 mm的不确定性。根据Pleiades测试数据验证模型的RMSE为1.17 mm（东西方向），1.46 mm（南北方向）和1.52 mm（垂直方向），其中三个本地GNSS站（6-50 km距离，IGS14/NNR框架，2019-2024）的垂直分量RMSE为1.98 mm。这种insar - pleades -深度学习方法为3D变形监测提供了可扩展的解决方案，推进了无gcp环境下的地震危害评估。

{"title":"Precise 3D crustal displacement retrieval in GCP-free environments: A geodetic and deep learning–assisted integration of InSAR and optical stereo data near the Denali Fault","authors":"Zahra Alizadeh Zakaria , Farshid Farnood Ahmadi , Hamid Ebadi","doi":"10.1016/j.rsase.2026.101894","DOIUrl":"10.1016/j.rsase.2026.101894","url":null,"abstract":"<div><div>Retrieving accurate 3D deformation fields from Interferometric Synthetic Aperture Radar)InSAR(line-of-sight (LOS) measurements is challenging because LOS data provide only one-dimensional motion, and the absence of ground control points (GCPs) in remote regions makes reliable 3D reconstruction even more difficult. This study introduces a deep learning-assisted approach to map 3D deformation fields without GCPs, integrating Pleiades stereo imagery with InSAR techniques over a 20 km × 20 km segment of the Denali Fault, Alaska. Initial 3D displacements from Pleiades, derived through DEM differencing and COSI-Corr, eliminate GCPs and reveal vertical displacements of ±10 mm (uplift/subsidence), with horizontal displacements of ±6.4 mm (east-west) and ±5.9 mm (north-south), consistent with the fault's right-lateral strike-slip kinematics and local GNSS IGS14/NNR velocities (2019–2024). These Pleiades displacements, combined with PS-InSAR rates and geological features like slope and Terrain Ruggedness Index (TRI), serve as inputs to a U-Net model that transforms LOS data into 3D fields, expanding displacement ranges to ±20 mm across all components. We enhance U-Net estimates with geodetic optimization and use Monte Carlo Dropout (10 samples) to quantify uncertainties of 0.1–0.3 mm for east-west and 0.5–0.8 mm for north-south and vertical displacements. Validation of the model against Pleiades test data yields RMSEs of 1.17 mm (east-west), 1.46 mm (north-south), and 1.52 mm (vertical), with an RMSE of 1.98 mm against the vertical component of three local GNSS stations (6–50 km distance, IGS14/NNR frame, 2019–2024). This InSAR-Pleiades-deep learning method offers a scalable solution for 3D deformation monitoring, advancing seismic hazard assessment in GCP-free environments.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"41 ","pages":"Article 101894"},"PeriodicalIF":4.5,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146077729","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Seasonal NDVI shifts: Assessing vegetation responses to hydro-climatic changes across diverse agro-climatic zones of India 季节性NDVI变化：评估印度不同农业气候带植被对水文气候变化的响应

IF 4.5 Q2 ENVIRONMENTAL SCIENCES

Remote Sensing Applications-Society and Environment

Pub Date : 2026-01-01 DOI: 10.1016/j.rsase.2026.101882

Venkadesh Samykannu, Sheshakumar Goroshi, Ramaraj Palanisamy, D.S. Pai, Mrutyunjay Mohapatra

This study examines four decades (1982–2022) of seasonal and inter-annual vegetation dynamics across diverse agro-climatic zones (ACZs) in India, focusing on the relationships between the Normalized Difference Vegetation Index (NDVI) and key hydro-climatic variables; soil moisture (SM), evapotranspiration (ET), rainfall (RF), and vapor pressure deficit (VPD) during the Kharif (monsoon) and Rabi (post-monsoon) seasons. Using the Global Inventory Monitoring and Modeling Studies (GIMMS) NDVI3g dataset, which represents overall vegetation greenness and predominantly reflects cropland areas within ACZs of India, linear regression and Mann-Kendall analyses revealed significant greening trends, with NDVI increasing from 0.49 to 0.57 in Kharif and from 0.41 to 0.51 in Rabi. Strongest positive trends occurred in the Lower and Trans-Gangetic Plains, while localized declines appeared in the Island Region. The results highlight soil moisture and evapotranspiration as dominant controls on vegetation productivity, indicating enhanced water availability and improved agricultural management. Distinct from earlier NDVI studies, this research integrates long-term hydro-climatic drivers with agro-climatic perspective, providing new evidence that seasonal NDVI is a sensitive indicator of crop-level resilience to climate variability. Findings support region-specific irrigation planning and adaptive strategies for sustainable agricultural development.

本研究考察了印度不同农业气气带（acz） 40年来的季节和年际植被动态，重点研究了归一化植被指数（NDVI）与关键水文气候变量之间的关系；在Kharif（季风）和Rabi（季风后）季节，土壤湿度（SM）、蒸散（ET）、降雨量（RF）和水汽压亏缺（VPD）。利用全球植被清查监测和建模研究（GIMMS） NDVI3g数据集，线性回归和Mann-Kendall分析显示了显著的绿化趋势，Kharif的NDVI从0.49增加到0.57，Rabi从0.41增加到0.51。该数据集代表了印度acz内的总体植被绿化率，主要反映了耕地面积。最明显的上升趋势出现在下游和跨恒河平原，而岛屿地区出现局部下降。结果表明，土壤水分和蒸散是植被生产力的主要控制因素，表明水分有效性得到提高，农业管理得到改善。与早期的NDVI研究不同，本研究将长期水文气候驱动因素与农业气候视角结合起来，提供了新的证据，证明季节性NDVI是作物对气候变率适应能力的敏感指标。研究结果支持区域灌溉规划和可持续农业发展适应性战略。

{"title":"Seasonal NDVI shifts: Assessing vegetation responses to hydro-climatic changes across diverse agro-climatic zones of India","authors":"Venkadesh Samykannu, Sheshakumar Goroshi, Ramaraj Palanisamy, D.S. Pai, Mrutyunjay Mohapatra","doi":"10.1016/j.rsase.2026.101882","DOIUrl":"10.1016/j.rsase.2026.101882","url":null,"abstract":"<div><div>This study examines four decades (1982–2022) of seasonal and inter-annual vegetation dynamics across diverse agro-climatic zones (ACZs) in India, focusing on the relationships between the Normalized Difference Vegetation Index (NDVI) and key hydro-climatic variables; soil moisture (SM), evapotranspiration (ET), rainfall (RF), and vapor pressure deficit (VPD) during the <em>Kharif</em> (monsoon) and <em>Rabi</em> (post-monsoon) seasons. Using the Global Inventory Monitoring and Modeling Studies (GIMMS) NDVI3g dataset, which represents overall vegetation greenness and predominantly reflects cropland areas within ACZs of India, linear regression and Mann-Kendall analyses revealed significant greening trends, with NDVI increasing from 0.49 to 0.57 in <em>Kharif</em> and from 0.41 to 0.51 in <em>Rabi</em>. Strongest positive trends occurred in the Lower and Trans-Gangetic Plains, while localized declines appeared in the Island Region. The results highlight soil moisture and evapotranspiration as dominant controls on vegetation productivity, indicating enhanced water availability and improved agricultural management. Distinct from earlier NDVI studies, this research integrates long-term hydro-climatic drivers with agro-climatic perspective, providing new evidence that seasonal NDVI is a sensitive indicator of crop-level resilience to climate variability. Findings support region-specific irrigation planning and adaptive strategies for sustainable agricultural development.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"41 ","pages":"Article 101882"},"PeriodicalIF":4.5,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145977175","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

On the use of post-classification change analysis for monitoring salt marsh extent in support of carbon inventory reporting 利用分类后变化分析监测盐沼程度，支持碳清单报告

IF 4.5 Q2 ENVIRONMENTAL SCIENCES

Remote Sensing Applications-Society and Environment

Pub Date : 2026-01-01 DOI: 10.1016/j.rsase.2025.101862

Elisha Richardson , Koreen Millard , Danika van Proosdij

Salt marshes are valuable blue carbon ecosystems that outperform terrestrial environments in their capacity to sequester carbon (per unit area). Natural salt marshes exhibit striking zonation in vegetation, which reflects their elevation in relation to tidal inundation. Natural salt marshes have been removed and degraded globally, and while the potential environmental benefits of salt marsh restoration and natural marsh conservation have been documented, many regions lack consistent mapping or monitoring efforts, partly due to their inaccessible nature and partly because of challenges in using satellite remote sensing in intertidal areas. The elevation and dominant vegetation within a salt marsh restoration site reflects in part their restoration status and maturity, which are in turn linked to their capacity for carbon storage and sequestration. Therefore, a lack of information about vegetation zonation in natural and restored salt marshes is a knowledge gap that inhibits our ability to report on any salt marsh extent changes, and subsequently their inclusion in greenhouse gas inventory reporting. Existing “global” models may not perform sufficiently in regional contexts, especially in megatidal regions such as the Bay of Fundy which experiences exceptional seasonal and tidal conditions. Demonstrated at both natural salt marshes and salt marsh restoration sites in the Bay of Fundy, this study presents a robust method for mapping of salt marshes using machine learning classification techniques. We leverage multitemporal and multisensor imagery from specific tidal stages to identify the characteristic vegetation of high elevation and low elevation salt marsh. The results indicate the importance of acquiring low tide imagery, and the inclusion of imagery from multiple seasons can improve classification accuracy. Predicted maps for 2020 and 2023 were used to produce “change data” and associated uncertainties, which may be combined with other components of activity data in carbon inventory reporting.

盐沼是宝贵的蓝碳生态系统，其固碳能力（每单位面积）优于陆地环境。天然盐沼在植被上表现出明显的地带性，这反映了它们与潮汐淹没有关的高程。在全球范围内，天然盐沼已经消失和退化，虽然盐沼恢复和自然沼泽保护的潜在环境效益已被记录下来，但许多地区缺乏一致的测绘或监测工作，部分原因是这些地区难以进入，部分原因是在潮间带地区使用卫星遥感存在挑战。盐沼恢复地的海拔高度和优势植被部分反映了其恢复状态和成熟度，这反过来又与它们的碳储存和固碳能力有关。因此，缺乏关于自然盐沼和恢复盐沼植被带的信息是一个知识缺口，它抑制了我们报告任何盐沼范围变化的能力，并随后将其纳入温室气体清单报告。现有的“全球”模式在区域背景下可能表现不佳，特别是在芬迪湾这样经历特殊季节和潮汐条件的巨型潮区。在芬迪湾的天然盐沼和盐沼恢复地点进行了演示，该研究提出了一种使用机器学习分类技术绘制盐沼地图的强大方法。我们利用来自特定潮汐阶段的多时相和多传感器图像来识别高海拔和低海拔盐沼的特征植被。结果表明获取低潮影像的重要性，多季节影像的融合可以提高分类精度。2020年和2023年的预测图用于生成“变化数据”和相关的不确定性，这些数据可能与碳清单报告中活动数据的其他组成部分相结合。

{"title":"On the use of post-classification change analysis for monitoring salt marsh extent in support of carbon inventory reporting","authors":"Elisha Richardson , Koreen Millard , Danika van Proosdij","doi":"10.1016/j.rsase.2025.101862","DOIUrl":"10.1016/j.rsase.2025.101862","url":null,"abstract":"<div><div>Salt marshes are valuable blue carbon ecosystems that outperform terrestrial environments in their capacity to sequester carbon (per unit area). Natural salt marshes exhibit striking zonation in vegetation, which reflects their elevation in relation to tidal inundation. Natural salt marshes have been removed and degraded globally, and while the potential environmental benefits of salt marsh restoration and natural marsh conservation have been documented, many regions lack consistent mapping or monitoring efforts, partly due to their inaccessible nature and partly because of challenges in using satellite remote sensing in intertidal areas. The elevation and dominant vegetation within a salt marsh restoration site reflects in part their restoration status and maturity, which are in turn linked to their capacity for carbon storage and sequestration. Therefore, a lack of information about vegetation zonation in natural and restored salt marshes is a knowledge gap that inhibits our ability to report on any salt marsh extent changes, and subsequently their inclusion in greenhouse gas inventory reporting. Existing “global” models may not perform sufficiently in regional contexts, especially in megatidal regions such as the Bay of Fundy which experiences exceptional seasonal and tidal conditions. Demonstrated at both natural salt marshes and salt marsh restoration sites in the Bay of Fundy, this study presents a robust method for mapping of salt marshes using machine learning classification techniques. We leverage multitemporal and multisensor imagery from specific tidal stages to identify the characteristic vegetation of high elevation and low elevation salt marsh. The results indicate the importance of acquiring low tide imagery, and the inclusion of imagery from multiple seasons can improve classification accuracy. Predicted maps for 2020 and 2023 were used to produce “change data” and associated uncertainties, which may be combined with other components of activity data in carbon inventory reporting.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"41 ","pages":"Article 101862"},"PeriodicalIF":4.5,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145926031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Integrating CA–Markov–ANN for spatiotemporal prediction of land use dynamics in a fragile Himalayan watershed 基于CA-Markov-ANN的脆弱喜马拉雅流域土地利用动态时空预测

IF 4.5 Q2 ENVIRONMENTAL SCIENCES

Remote Sensing Applications-Society and Environment

Pub Date : 2026-01-01 DOI: 10.1016/j.rsase.2025.101856

Pawan Kumar Thakur , Praveen Kumar Thakur , Raj Kumar Verma , Biswajeet Pradhan

Predicting future Land-Use/Land-Cover (LULC) changes is essential for sustainable resource management and environmental monitoring, particularly in ecologically fragile high-altitude Himalayan watersheds like the Parbati Watershed (PW), where biodiversity, hydrology, and climate stability are increasingly threatened. However, limited studies have explored integrated, data-driven LULC modeling approaches for high-altitude Himalayan watersheds, leaving a critical gap in understanding the spatiotemporal evolution of these sensitive landscapes. This study addresses this gap by proposing a novel Cellular Automata (CA)-Markov chain (MC)-based Artificial Neural Network (CA–MC-ANN) framework, implemented through a Multi-Layer Perceptron (MLP) prediction architecture and uniquely tailored to the PW. We assess past LULC dynamics (1989–2023) and project future scenarios (2035, 2045) to understand transformations driven by intertwined anthropogenic pressures and climate change. Key findings reveal a rapidly transforming landscape where glacier/snow cover has decreased from ∼37.66 % (1989) to ∼21.61 % (2023), projected to fall to ∼13.47 % by 2045—a ∼24.19 % cumulative loss (∼-0.43 %/yr) driven by high-altitude warming. In contrast, built-up/settlement areas increased from ∼0.26 % (1989) to ∼0.80 % (2023) and are projected to reach ∼1.21 % by 2045—a ∼0.95 % cumulative gain (∼+0.02 %/yr), reflecting tourism boosts, hydroelectric projects (HEPs), and rapid infrastructure expansion. Alongside, Himalayan Moist Temperate Forests (HMTF) declined from ∼14.95 % (1989) to ∼14.06 % (2023) and are also projected to decline to ∼13.75 % by 2045—a ∼-1.20 % cumulative loss (∼-0.02 %/yr), indicating mounting pressure on natural ecosystems. These trends highlight accelerating glacial shrinkage, rapid tourism and development expansion, and land degradation. These findings underscore the urgent need for integrated spatial analysis and predictive modelling to inform regional conservation, sustainable land management, and resilient development strategies. Implementing comprehensive LULC and biodiversity impact assessments is critical for enhancing environmental resilience and ensuring long-term socio-ecological sustainability in the ecologically sensitive Himalayan region.

预测未来土地利用/土地覆盖（LULC）变化对于可持续资源管理和环境监测至关重要，特别是在生态脆弱的喜马拉雅高海拔流域，如帕尔巴蒂流域（PW），生物多样性、水文和气候稳定性日益受到威胁。然而，有限的研究已经探索了高海拔喜马拉雅流域的综合、数据驱动的LULC建模方法，在理解这些敏感景观的时空演变方面留下了关键的空白。本研究通过提出一种新的基于元胞自动机(CA)-马尔可夫链（MC）的人工神经网络（CA - MC- ann）框架来解决这一差距，该框架通过多层感知器（MLP）预测架构实现，并为PW量身定制。我们评估了过去的LULC动态（1989-2023），并预测了未来情景（2035年，2045年），以了解人为压力和气候变化交织驱动的转变。主要发现揭示了一个快速变化的景观，其中冰川/积雪覆盖已从~ 37.66%（1989年）减少到~ 21.61%（2023年），预计到2045年将降至~ 13.47%，在高海拔变暖的驱动下，累计损失为~ 24.19%（~ - 0.43% /年）。相比之下，建成区/定居区从0.26%（1989年）增加到0.80%（2023年），预计到2045年将达到1.21%——累计收益为0.95%（每年+ 0.02%），反映了旅游业的发展、水电项目（HEPs）和基础设施的快速扩张。与此同时，喜马拉雅湿温带森林（HMTF）从~ 14.95%（1989年）下降到~ 14.06%（2023年），预计到2045年也将下降到~ 13.75%——累计损失为~ - 1.20%（~ - 0.02% /年），表明自然生态系统面临的压力越来越大。这些趋势突出表明冰川加速萎缩、旅游业和开发的迅速扩张以及土地退化。这些发现强调了对综合空间分析和预测建模的迫切需要，以便为区域保护、可持续土地管理和弹性发展战略提供信息。在生态敏感的喜马拉雅地区，实施全面的土地利用和生物多样性影响评估对于增强环境恢复力和确保长期的社会生态可持续性至关重要。

{"title":"Integrating CA–Markov–ANN for spatiotemporal prediction of land use dynamics in a fragile Himalayan watershed","authors":"Pawan Kumar Thakur , Praveen Kumar Thakur , Raj Kumar Verma , Biswajeet Pradhan","doi":"10.1016/j.rsase.2025.101856","DOIUrl":"10.1016/j.rsase.2025.101856","url":null,"abstract":"<div><div>Predicting future Land-Use/Land-Cover (LULC) changes is essential for sustainable resource management and environmental monitoring, particularly in ecologically fragile high-altitude Himalayan watersheds like the Parbati Watershed (PW), where biodiversity, hydrology, and climate stability are increasingly threatened. However, limited studies have explored integrated, data-driven LULC modeling approaches for high-altitude Himalayan watersheds, leaving a critical gap in understanding the spatiotemporal evolution of these sensitive landscapes. This study addresses this gap by proposing a novel Cellular Automata (CA)-Markov chain (MC)-based Artificial Neural Network (CA–MC-ANN) framework, implemented through a Multi-Layer Perceptron (MLP) prediction architecture and uniquely tailored to the PW. We assess past LULC dynamics (1989–2023) and project future scenarios (2035, 2045) to understand transformations driven by intertwined anthropogenic pressures and climate change. Key findings reveal a rapidly transforming landscape where glacier/snow cover has decreased from ∼37.66 % (1989) to ∼21.61 % (2023), projected to fall to ∼13.47 % by 2045—a ∼24.19 % cumulative loss (∼-0.43 %/yr) driven by high-altitude warming. In contrast, built-up/settlement areas increased from ∼0.26 % (1989) to ∼0.80 % (2023) and are projected to reach ∼1.21 % by 2045—a ∼0.95 % cumulative gain (∼+0.02 %/yr), reflecting tourism boosts, hydroelectric projects (HEPs), and rapid infrastructure expansion. Alongside, Himalayan Moist Temperate Forests (HMTF) declined from ∼14.95 % (1989) to ∼14.06 % (2023) and are also projected to decline to ∼13.75 % by 2045—a ∼-1.20 % cumulative loss (∼-0.02 %/yr), indicating mounting pressure on natural ecosystems. These trends highlight accelerating glacial shrinkage, rapid tourism and development expansion, and land degradation. These findings underscore the urgent need for integrated spatial analysis and predictive modelling to inform regional conservation, sustainable land management, and resilient development strategies. Implementing comprehensive LULC and biodiversity impact assessments is critical for enhancing environmental resilience and ensuring long-term socio-ecological sustainability in the ecologically sensitive Himalayan region.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"41 ","pages":"Article 101856"},"PeriodicalIF":4.5,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145926022","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Climate and environmental drivers of dengue expansion in São Paulo, Brazil: An ecological niche modelling approach 巴西圣保罗登革热扩张的气候和环境驱动因素：生态位建模方法

IF 4.5 Q2 ENVIRONMENTAL SCIENCES

Remote Sensing Applications-Society and Environment

Pub Date : 2026-01-01 DOI: 10.1016/j.rsase.2025.101844

Iuri Valerio Graciano Borges , Tercio Ambrizzi , Anwar Musah , Luiza C. Campos

Dengue outbreaks in São Paulo State are expanding, driven by a complex interplay of environmental and demographic factors. This study employs an ecological niche model (ENM) to investigate the drivers of dengue suitability across three major epidemic years: 2011, 2015, and 2019. Utilising a robust methodological framework, including semi-annual environmental data and spatially explicit cross-validation, it was found that population density was the most influential predictor of outbreak suitability in all three years (63.4 % contribution in 2011, 91.6 % in 2015, and 48.6 % in 2019). Secondary drivers shifted between epidemics, with maximum temperature being most relevant in 2011 (26.3 %) and the Normalized Difference Vegetation Index (NDVI) gaining importance in 2019 (18.5 %). Spatially, the analysis revealed a highly dynamic risk landscape, characterised by a massive statewide expansion of high-suitability zones in 2015, followed by a significant contraction and northward shift in 2019. The model's predictive performance was strong for 2011 and 2015, but declined in 2019, suggesting a less distinct environmental signature for that year's outbreak. These findings indicate that urban structure is the primary determinant of dengue suitability, while climatic and vegetation factors modulate risk differently across epidemics with varying characteristics.

由于环境和人口因素的复杂相互作用，圣保罗州的登革热疫情正在扩大。本研究采用生态位模型（ENM）对2011年、2015年和2019年三个主要流行年登革热适宜性的驱动因素进行了研究。利用强大的方法框架，包括半年度环境数据和空间明确的交叉验证，发现人口密度是所有三年暴发适宜性的最具影响力的预测因子（2011年贡献63.4%，2015年贡献91.6%，2019年贡献48.6%）。次级驱动因素在不同疫情之间发生了变化，最高气温在2011年最相关（26.3%），归一化植被指数（NDVI）在2019年变得越来越重要（18.5%）。从空间上看，分析显示了一个高度动态的风险格局，其特征是2015年高适宜性区域在全州范围内大规模扩张，随后在2019年大幅收缩并向北转移。该模型在2011年和2015年的预测表现强劲，但在2019年有所下降，这表明当年疫情爆发的环境特征不那么明显。这些发现表明，城市结构是登革热适宜性的主要决定因素，而气候和植被因素在不同特征的疫情中调节风险的方式不同。

{"title":"Climate and environmental drivers of dengue expansion in São Paulo, Brazil: An ecological niche modelling approach","authors":"Iuri Valerio Graciano Borges , Tercio Ambrizzi , Anwar Musah , Luiza C. Campos","doi":"10.1016/j.rsase.2025.101844","DOIUrl":"10.1016/j.rsase.2025.101844","url":null,"abstract":"<div><div>Dengue outbreaks in São Paulo State are expanding, driven by a complex interplay of environmental and demographic factors. This study employs an ecological niche model (ENM) to investigate the drivers of dengue suitability across three major epidemic years: 2011, 2015, and 2019. Utilising a robust methodological framework, including semi-annual environmental data and spatially explicit cross-validation, it was found that population density was the most influential predictor of outbreak suitability in all three years (63.4 % contribution in 2011, 91.6 % in 2015, and 48.6 % in 2019). Secondary drivers shifted between epidemics, with maximum temperature being most relevant in 2011 (26.3 %) and the Normalized Difference Vegetation Index (NDVI) gaining importance in 2019 (18.5 %). Spatially, the analysis revealed a highly dynamic risk landscape, characterised by a massive statewide expansion of high-suitability zones in 2015, followed by a significant contraction and northward shift in 2019. The model's predictive performance was strong for 2011 and 2015, but declined in 2019, suggesting a less distinct environmental signature for that year's outbreak. These findings indicate that urban structure is the primary determinant of dengue suitability, while climatic and vegetation factors modulate risk differently across epidemics with varying characteristics.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"41 ","pages":"Article 101844"},"PeriodicalIF":4.5,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145926033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimising deep learning for building extraction: Dataset efficiency and model backbones under data constraints 优化深度学习用于构建提取：数据约束下的数据集效率和模型主干

IF 4.5 Q2 ENVIRONMENTAL SCIENCES

Remote Sensing Applications-Society and Environment

Pub Date : 2026-01-01 DOI: 10.1016/j.rsase.2026.101876

Dung T. Pham , Thuong V. Tran , Xuan Zhu , Hung N. Pham

Accurate building extraction from very high-resolution (VHR) satellite imagery is critical for urban planning, disaster response, and environmental monitoring. However, the performance of deep learning models remains highly sensitive to training sample size, model complexity, and learning strategy, especially in data-scarce scenarios. Here, we systematically evaluated the DeepLabV3+ architecture with ResNet backbones (i.e., ResNet-18, 50, 101, 152) across varying training sample sizes (i.e., 20–120 % of the primary WHU dataset) and three training approaches: random initialisation, ImageNet pre-training, and pre-training with data augmentation. Our results revealed a U-shaped relationship between dataset size and performance, with segmentation accuracy peaking at full dataset usage and declining when additional samples introduce redundancy. Peak performance reached 88.0 % IoU and 93.2 % F1-score under optimised configuration, while shallower models achieved optimal performance under limited data availability. We found that hybrid learning strategies are essential for mitigating overfitting and achieving high accuracy, with transfer learning improving accuracy by 7.9 % IoU (5.8 % F1-score), and data augmentation offering an additional 1–3 % IoU (0.2–2.3 % F1-score) gain in low-data settings (≤40 %). Deeper networks (ResNet-101/152) achieved superior performance only when trained with ≥60 % of the dataset and appropriate regularisation. The stability of these data-dependent model selection patterns was further confirmed through external validation on the Japan Building Dataset, demonstrating transferability across geographic contexts. Our findings yield practical and generalisable guidelines: (i) avoiding unnecessary dataset expansion, (ii) prioritising transfer learning and augmentation when data is scarce, and (iii) aligning model depth with data availability. By explicitly linking model selection to data availability, this study supports efficient and reliable deployment of deep learning for urban analytics and disaster response under realistic annotation constraints.

从高分辨率（VHR）卫星图像中准确提取建筑物对城市规划、灾害响应和环境监测至关重要。然而，深度学习模型的性能仍然对训练样本量、模型复杂性和学习策略高度敏感，特别是在数据稀缺的情况下。在这里，我们系统地评估了DeepLabV3+架构与ResNet主干（即ResNet- 18,50,101,152）在不同的训练样本量（即20 - 120%的主要WHU数据集）和三种训练方法：随机初始化，ImageNet预训练和数据增强预训练。我们的结果揭示了数据集大小和性能之间的u形关系，分割精度在完全使用数据集时达到峰值，当额外的样本引入冗余时下降。在优化配置下，峰值性能达到88.0% IoU和93.2% F1-score，而较浅的模型在有限的数据可用性下实现了最佳性能。我们发现混合学习策略对于减轻过拟合和实现高精度至关重要，迁移学习将准确性提高了7.9% IoU （5.8% f1分数），数据增强在低数据设置（≤40%）中提供了额外的1- 3% IoU （0.2 - 2.3% f1分数）增益。深度网络（ResNet-101/152）只有在使用≥60%的数据集和适当的正则化进行训练时才能获得优异的性能。通过对日本建筑数据集的外部验证，进一步证实了这些依赖数据的模型选择模式的稳定性，证明了跨地理环境的可移植性。我们的研究结果产生了实用和通用的指导方针：(i)避免不必要的数据集扩展，（ii）在数据稀缺时优先考虑迁移学习和增强，以及（iii）将模型深度与数据可用性保持一致。通过明确地将模型选择与数据可用性联系起来，本研究支持在现实注释约束下高效可靠地部署深度学习用于城市分析和灾害响应。

{"title":"Optimising deep learning for building extraction: Dataset efficiency and model backbones under data constraints","authors":"Dung T. Pham , Thuong V. Tran , Xuan Zhu , Hung N. Pham","doi":"10.1016/j.rsase.2026.101876","DOIUrl":"10.1016/j.rsase.2026.101876","url":null,"abstract":"<div><div>Accurate building extraction from very high-resolution (VHR) satellite imagery is critical for urban planning, disaster response, and environmental monitoring. However, the performance of deep learning models remains highly sensitive to training sample size, model complexity, and learning strategy, especially in data-scarce scenarios. Here, we systematically evaluated the DeepLabV3+ architecture with ResNet backbones (i.e., ResNet-18, 50, 101, 152) across varying training sample sizes (i.e., 20–120 % of the primary WHU dataset) and three training approaches: random initialisation, ImageNet pre-training, and pre-training with data augmentation. Our results revealed a U-shaped relationship between dataset size and performance, with segmentation accuracy peaking at full dataset usage and declining when additional samples introduce redundancy. Peak performance reached 88.0 % IoU and 93.2 % F1-score under optimised configuration, while shallower models achieved optimal performance under limited data availability. We found that hybrid learning strategies are essential for mitigating overfitting and achieving high accuracy, with transfer learning improving accuracy by 7.9 % IoU (5.8 % F1-score), and data augmentation offering an additional 1–3 % IoU (0.2–2.3 % F1-score) gain in low-data settings (≤40 %). Deeper networks (ResNet-101/152) achieved superior performance only when trained with ≥60 % of the dataset and appropriate regularisation. The stability of these data-dependent model selection patterns was further confirmed through external validation on the Japan Building Dataset, demonstrating transferability across geographic contexts. Our findings yield practical and generalisable guidelines: (i) avoiding unnecessary dataset expansion, (ii) prioritising transfer learning and augmentation when data is scarce, and (iii) aligning model depth with data availability. By explicitly linking model selection to data availability, this study supports efficient and reliable deployment of deep learning for urban analytics and disaster response under realistic annotation constraints.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"41 ","pages":"Article 101876"},"PeriodicalIF":4.5,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145977871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Comparative assessment of machine learning and band ratios for robust water quality assessment in inland waters 机器学习和频带比率在内陆水域稳健水质评估中的比较评估

IF 4.5 Q2 ENVIRONMENTAL SCIENCES

Remote Sensing Applications-Society and Environment

Pub Date : 2026-01-01 DOI: 10.1016/j.rsase.2026.101878

Laura Cáceres , Jorge Rodríguez-Chueca , David J. Vicente

Remote sensing offers a valuable complement to traditional in situ monitoring for water quality in reservoirs, particularly under increasing pressures from eutrophication and climate change. This study integrates Sentinel-2 imagery with field data to estimate chlorophyll-a (Chla), cyanobacterial chlorophyll-a (Cyano), turbidity (Turb), and Secchi Disk Depth (SDD) in ten reservoirs in the Madrid region. Five modelling scenarios were tested: a semi-empirical band ratios (BR) model and four Random Forest (RF) machine learning (ML) models with different input combinations, including spectral bands, BR, trophic classification (via k-means), and seasonal variables (month-of-year sine and cosine). To ensure robustness with a relatively small dataset (N = 439), 100 random iterations were run per scenario. The semi-empirical model performed best for Turb (R² = 0.86, RMSE = 1.89), while the most complete RF scenario (Scenario IV) yielded the highest accuracy for Chla (R² = 0.54, RMSE = 10.66), Cyano (R² = 0.59, RMSE = 6.90) and SDD (R² = 0.77, RMSE = 1.01). Lower performance for Chla and Cyano was linked to data imbalance at high concentrations. Shapley Additive Explanations (SHAP) revealed trophic status and red/red-edge BR as the most influential predictors, highlighting the central role of nutrient enrichment, phytoplankton biomass and optical properties in shaping water quality, while seasonal variables further explained transparency patterns. These findings demonstrate the utility of integrating RS and ML for scalable and cost-effective water quality monitoring and provide insights into ecological processes in reservoir environments, supporting more informed water management strategies.

遥感是对水库水质传统就地监测的宝贵补充，特别是在富营养化和气候变化的压力日益增大的情况下。该研究将Sentinel-2图像与野外数据相结合，估算了马德里地区10个水库的叶绿素-a （Chla）、蓝藻叶绿素-a （Cyano）、浊度（Turb）和塞奇盘深度（SDD）。测试了五种建模场景：半经验波段比率（BR）模型和四个随机森林（RF）机器学习（ML）模型，这些模型具有不同的输入组合，包括光谱波段、BR、营养分类（通过k-means）和季节变量（月份的正弦和余弦）。为了确保相对较小的数据集（N = 439）的鲁棒性，每个场景运行100次随机迭代。半经验模型对Turb的准确度最好（R2 = 0.86, RMSE = 1.89），而最完整的RF情景（scenario IV）对Chla （R2 = 0.54, RMSE = 10.66）、Cyano （R2 = 0.59, RMSE = 6.90）和SDD （R2 = 0.77, RMSE = 1.01）的准确度最高。Chla和Cyano较低的性能与高浓度下的数据不平衡有关。Shapley加性解释（Shapley Additive explanatory， SHAP）揭示了营养状况和红边BR是影响最大的预测因子，强调了营养物富集、浮游植物生物量和光学特性在塑造水质中的核心作用，而季节变量进一步解释了透明度模式。这些发现证明了将RS和ML集成在一起用于可扩展且具有成本效益的水质监测的实用性，并为水库环境中的生态过程提供了见解，支持更明智的水管理策略。

{"title":"Comparative assessment of machine learning and band ratios for robust water quality assessment in inland waters","authors":"Laura Cáceres , Jorge Rodríguez-Chueca , David J. Vicente","doi":"10.1016/j.rsase.2026.101878","DOIUrl":"10.1016/j.rsase.2026.101878","url":null,"abstract":"<div><div>Remote sensing offers a valuable complement to traditional <em>in</em> situ monitoring for water quality in reservoirs, particularly under increasing pressures from eutrophication and climate change. This study integrates Sentinel-2 imagery with field data to estimate chlorophyll-a (Chla), cyanobacterial chlorophyll-a (Cyano), turbidity (Turb), and Secchi Disk Depth (SDD) in ten reservoirs in the Madrid region. Five modelling scenarios were tested: a semi-empirical band ratios (BR) model and four Random Forest (RF) machine learning (ML) models with different input combinations, including spectral bands, BR, trophic classification (via k-means), and seasonal variables (month-of-year sine and cosine). To ensure robustness with a relatively small dataset (N = 439), 100 random iterations were run per scenario. The semi-empirical model performed best for Turb (R<sup>2</sup> = 0.86, RMSE = 1.89), while the most complete RF scenario (Scenario IV) yielded the highest accuracy for Chla (R<sup>2</sup> = 0.54, RMSE = 10.66), Cyano (R<sup>2</sup> = 0.59, RMSE = 6.90) and SDD (R<sup>2</sup> = 0.77, RMSE = 1.01). Lower performance for Chla and Cyano was linked to data imbalance at high concentrations. Shapley Additive Explanations (SHAP) revealed trophic status and red/red-edge BR as the most influential predictors, highlighting the central role of nutrient enrichment, phytoplankton biomass and optical properties in shaping water quality, while seasonal variables further explained transparency patterns. These findings demonstrate the utility of integrating RS and ML for scalable and cost-effective water quality monitoring and provide insights into ecological processes in reservoir environments, supporting more informed water management strategies.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"41 ","pages":"Article 101878"},"PeriodicalIF":4.5,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145977872","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Integrating post-rainfall multispectral satellite-derived features and multi-source datasets to enhance soil salinity mapping accuracy 整合降雨后多光谱卫星特征和多源数据集，提高土壤盐度制图精度

IF 4.5 Q2 ENVIRONMENTAL SCIENCES

Remote Sensing Applications-Society and Environment

Pub Date : 2026-01-01 DOI: 10.1016/j.rsase.2026.101896

Jamal-Eddine Ouzemou , Ahmed Laamrani , Ali EL Battay , Joann K. Whalen , Abdelghani Chehbouni

Soil salinity poses a critical threat to agricultural productivity in arid and semi-arid regions, particularly under changing climate. In Morocco's Sehb El Masjoune area, we hypothesize that post-rainfall terrain dynamics and soil spectral responses drive the spatial variability of surface salinity. This study integrates Sentinel-2, Landsat-9, and PlanetScope imagery with field-measured electrical conductivity and machine learning. It evaluates three hypotheses: (i) micro-topographic depressions retain moisture and promote localized salt accumulation; (ii) soil composition clusters influence differential salt retention; and (iii) combining multi-source data improves salinity mapping. Two novel post-rainfall proxies were developed from PlanetScope imagery. The first, the Depression Proxy (DP), identifies moisture-retaining concavities. The second, the Soil Clusters Proxy (SCP), groups soils based on post-rainfall spectral responses that are linked to texture and moisture properties. These were integrated with spectral indices and terrain variables into three modeling approaches using RF and GBR. Sentinel-2 combined with GBR and DP feature achieved the highest accuracy on an independent test set (R² = 0.85), identifying concave terrain as persistent salinity location and highlighting the role of surface topography (i.e., micro-depressions) in salinity distribution. Categorical accuracy confirmed that 56 % of samples were assigned to the exact soil salinity class and 80 % within ±1 class. Additionally, seasonal changes in predicted salinity were also examined using consistent spectral signatures between wet and dry imagery; however, due to the lack of wet-season ground truth, the resulting map represents qualitative spatial trends rather than validated salinity estimates. This process-informed Earth Observation-based framework improves the accuracy and interpretability of salinity mapping.

土壤盐分对干旱和半干旱地区的农业生产力构成严重威胁，特别是在气候变化的情况下。在摩洛哥的Sehb El Masjoune地区，我们假设降雨后地形动力学和土壤光谱响应驱动了地表盐度的空间变异。这项研究将Sentinel-2、Landsat-9和PlanetScope图像与现场测量的电导率和机器学习相结合。它评估了三个假设：(1)微地形洼地保持水分并促进局部盐积聚；㈡土壤组成簇影响不同的盐潴留；(3)多源数据的结合提高了盐度成图的质量。从PlanetScope图像中开发了两个新的降雨后代用物。第一种是凹陷代理（DP），它能识别出保湿凹陷。第二个是土壤集群代理（SCP），根据与质地和水分特性相关的降雨后光谱响应对土壤进行分组。将这些数据与光谱指数和地形变量集成到使用RF和GBR的三种建模方法中。Sentinel-2结合GBR和DP特征在独立测试集上获得了最高的精度（R2 = 0.85），将凹地形识别为持续的盐度位置，并突出地表地形（即微洼地）在盐度分布中的作用。分类精度证实56%的样品被分配到精确的土壤盐度类别，80%在±1类别内。此外，还使用干湿图像之间一致的光谱特征来检查预测盐度的季节变化；然而，由于缺乏雨季地面的真实情况，所得的地图代表定性的空间趋势，而不是经过验证的盐度估计。这种基于过程的地球观测框架提高了盐度制图的准确性和可解释性。

{"title":"Integrating post-rainfall multispectral satellite-derived features and multi-source datasets to enhance soil salinity mapping accuracy","authors":"Jamal-Eddine Ouzemou , Ahmed Laamrani , Ali EL Battay , Joann K. Whalen , Abdelghani Chehbouni","doi":"10.1016/j.rsase.2026.101896","DOIUrl":"10.1016/j.rsase.2026.101896","url":null,"abstract":"<div><div>Soil salinity poses a critical threat to agricultural productivity in arid and semi-arid regions, particularly under changing climate. In Morocco's Sehb El Masjoune area, we hypothesize that post-rainfall terrain dynamics and soil spectral responses drive the spatial variability of surface salinity. This study integrates Sentinel-2, Landsat-9, and PlanetScope imagery with field-measured electrical conductivity and machine learning. It evaluates three hypotheses: (i) micro-topographic depressions retain moisture and promote localized salt accumulation; (ii) soil composition clusters influence differential salt retention; and (iii) combining multi-source data improves salinity mapping. Two novel post-rainfall proxies were developed from PlanetScope imagery. The first, the Depression Proxy (DP), identifies moisture-retaining concavities. The second, the Soil Clusters Proxy (SCP), groups soils based on post-rainfall spectral responses that are linked to texture and moisture properties. These were integrated with spectral indices and terrain variables into three modeling approaches using RF and GBR. Sentinel-2 combined with GBR and DP feature achieved the highest accuracy on an independent test set (R<sup>2</sup> = 0.85), identifying concave terrain as persistent salinity location and highlighting the role of surface topography (i.e., micro-depressions) in salinity distribution. Categorical accuracy confirmed that 56 % of samples were assigned to the exact soil salinity class and 80 % within ±1 class. Additionally, seasonal changes in predicted salinity were also examined using consistent spectral signatures between wet and dry imagery; however, due to the lack of wet-season ground truth, the resulting map represents qualitative spatial trends rather than validated salinity estimates. This process-informed Earth Observation-based framework improves the accuracy and interpretability of salinity mapping.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"41 ","pages":"Article 101896"},"PeriodicalIF":4.5,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146077731","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0