Remote Sensing Applications-Society and Environment最新文献

Warming trends in the Nile Delta: A high-resolution Spatial statistical approach 尼罗河三角洲变暖趋势：高分辨率空间统计方法

IF 3.8 Q2 ENVIRONMENTAL SCIENCES

Remote Sensing Applications-Society and Environment

Pub Date : 2024-11-24 DOI: 10.1016/j.rsase.2024.101408

Faten Nahas , Islam Hamdi , Mohamed Hereher , Martina Zelenakova , Ahmed M. El Kenawy

The Nile Delta, a region of historical significance, is facing significant environmental changes driven by climate change. This study employs a novel pixel-level spatial statistical analysis to assess the intensity and trends in the daytime and nighttime urban heat island (UHI) from 2003 to 2021. We employed high-resolution data from the Global Artificial Impermeable Area (GAIA) dataset (30 m), land surface temperature (LST) from the MODIS Aqua satellite 1000 m, and the MOD13A3 Normalized Difference Vegetation Index (NDVI) (1000 m). Bivariate choropleth maps were used to illustrate the spatial relationships between daytime and nighttime LST and NDVI. Ordinary least squares (OLS) regression method was used to calculate the trend for each pixel and the Mann-Kendall test was used to assess the statistical significance of the trend at 95% confidence level (p < 0.05). The central and southern regions of the delta experienced significant LST increases, highlighting the risk of warming due to vegetation degradation. Specifically, the diurnal LST trend ranged from −0.46 °C to 0.34 °C/year, while the nocturnal trend ranged from −0.12 °C to 0.26 °C/year. Spatially, the study also indicates cooling trends in coastal cities such as Port Said, New Damietta and Alexandria due to the moderate influence of the Mediterranean Sea. In contrast, the inland and southern Delta cities are warming rapidly. The relationship between diurnal UHI average and the NDVI showed a modest negative correlation (R = −0.31, p < 0.0001). This association was much stronger at night, with a negative correlation of (R = −0.71, P < 0.0001) A strong negative correlation between diurnal UHI trend and NDVI (R = −0.68, p < 0.0001). The relationship between nocturnal UHI trend and NDVI is negative (R = −0.61, p < 0.0001). The analysis reveals that 13 cities exhibited significant warming during the daytime, compared to 35 cities at night. The results highlight the importance of pixel-level data to accurately assess environmental changes and inform urban planning strategies to mitigate the effects of warming on the Nile Delta.

尼罗河三角洲是一个具有历史意义的地区，在气候变化的推动下，它正面临着重大的环境变化。本研究采用一种新颖的像素级空间统计分析方法，对2003 - 2021年中国城市白天和夜间热岛强度及其变化趋势进行了评估。利用全球人工不透水面积（GAIA）数据集（30 m）的高分辨率数据、MODIS Aqua卫星（1000 m）的陆地表面温度（LST）数据和MOD13A3归一化植被指数（NDVI）数据（1000 m），利用二元地形图分析昼夜地表温度与NDVI的空间关系。使用普通最小二乘（OLS）回归方法计算每个像素点的趋势，并使用Mann-Kendall检验在95%置信水平上评估趋势的统计学显著性(p <；0.05)。三角洲中部和南部地区地表温度显著升高，突出了植被退化导致的变暖风险。其中，日变化趋势为- 0.46°C ~ 0.34°C/年，夜变化趋势为- 0.12°C ~ 0.26°C/年。从空间上看，该研究还表明，由于地中海的适度影响，塞得港、新达米埃塔和亚历山大等沿海城市也出现了降温趋势。相比之下，内陆和南部三角洲城市正在迅速变暖。日平均热岛指数与NDVI呈适度负相关(R = - 0.31, p <；0.0001)。这种关联在夜间更为强烈，呈负相关(R = - 0.71, P <；0.0001)日UHI趋势与NDVI呈显著负相关(R = - 0.68, p <；0.0001)。夜间UHI趋势与NDVI呈负相关(R = - 0.61, p <；0.0001)。分析显示，13个城市在白天表现出明显的变暖，而35个城市在夜间表现出明显的变暖。研究结果强调了像素级数据对准确评估环境变化的重要性，并为城市规划策略提供信息，以减轻气候变暖对尼罗河三角洲的影响。

{"title":"Warming trends in the Nile Delta: A high-resolution Spatial statistical approach","authors":"Faten Nahas , Islam Hamdi , Mohamed Hereher , Martina Zelenakova , Ahmed M. El Kenawy","doi":"10.1016/j.rsase.2024.101408","DOIUrl":"10.1016/j.rsase.2024.101408","url":null,"abstract":"<div><div>The Nile Delta, a region of historical significance, is facing significant environmental changes driven by climate change. This study employs a novel pixel-level spatial statistical analysis to assess the intensity and trends in the daytime and nighttime urban heat island (UHI) from 2003 to 2021. We employed high-resolution data from the Global Artificial Impermeable Area (GAIA) dataset (30 m), land surface temperature (LST) from the MODIS Aqua satellite 1000 m, and the MOD13A3 Normalized Difference Vegetation Index (NDVI) (1000 m). Bivariate choropleth maps were used to illustrate the spatial relationships between daytime and nighttime LST and NDVI. Ordinary least squares (OLS) regression method was used to calculate the trend for each pixel and the Mann-Kendall test was used to assess the statistical significance of the trend at 95% confidence level (p < 0.05). The central and southern regions of the delta experienced significant LST increases, highlighting the risk of warming due to vegetation degradation. Specifically, the diurnal LST trend ranged from −0.46 °C to 0.34 °C/year, while the nocturnal trend ranged from −0.12 °C to 0.26 °C/year. Spatially, the study also indicates cooling trends in coastal cities such as Port Said, New Damietta and Alexandria due to the moderate influence of the Mediterranean Sea. In contrast, the inland and southern Delta cities are warming rapidly. The relationship between diurnal UHI average and the NDVI showed a modest negative correlation (R = −0.31, p < 0.0001). This association was much stronger at night, with a negative correlation of (R = −0.71, P < 0.0001) A strong negative correlation between diurnal UHI trend and NDVI (R = −0.68, p < 0.0001). The relationship between nocturnal UHI trend and NDVI is negative (R = −0.61, p < 0.0001). The analysis reveals that 13 cities exhibited significant warming during the daytime, compared to 35 cities at night. The results highlight the importance of pixel-level data to accurately assess environmental changes and inform urban planning strategies to mitigate the effects of warming on the Nile Delta.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101408"},"PeriodicalIF":3.8,"publicationDate":"2024-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142748002","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

Improving the estimation approach of percentage of impervious area for the storm water management model — A case study of the Zengwen reservoir watershed, Taiwan 改进暴雨管理模型中不透水面积百分比的估算方法 - 台湾曾文水库流域案例研究

IF 3.8 Q2 ENVIRONMENTAL SCIENCES

Remote Sensing Applications-Society and Environment

Pub Date : 2024-11-22 DOI: 10.1016/j.rsase.2024.101409

Chih-Wei Chuang, Ming-Huei Chen, Wen-Yan Zhang

The Zengwen Reservoir, located within the Zengwen River watershed, is a crucial water supply source in southern Taiwan. Water resources can be estimated using the rainfall-runoff model of the Storm Water Management Model (SWMM). However, the percentage of impervious area (PIA) is one of the significant factors influencing the SWMM. The purpose of this study is to utilize remote sensing imagery to rapidly and accurately estimate land use as PIA for the SWMM rainfall-runoff model. The rainfall-runoff model of SWMM was calibrated and validated based on observed discharge data in 2005 and 2017. The results of goodness-of-fit indicators of NSE value and R² value showed in the acceptable range of 0.745, 0.764 in 2005, 0.715, and 0.883 in 2007, respectively. The modified composite of the built-up index and PIA (MCBI-PIA) was used for rainfall-runoff simulation in 2005, 2009, 2014, 2017, and 2021. The simulation results revealed the NSE value varied from 0.484 to 0.851, and the R² value between 0.519 and 0.894 which represented a statistically acceptable performance of the simulation model. It indicates that the proposed method can be applied to estimate the PIA for land use patterns during different periods and utilized as the actual PIA for rainfall-runoff simulation with the SWMM.

曾文水库位于曾文溪流域内，是台湾南部重要的供水水源。水资源可利用暴雨管理模型（SWMM）的降雨-径流模型进行估算。然而，不透水面积百分比（PIA）是影响 SWMM 的重要因素之一。本研究的目的是利用遥感图像快速、准确地估算土地利用情况，将其作为 SWMM 雨量-径流模型的不透水面积百分比。基于 2005 年和 2017 年的观测排水数据，对 SWMM 雨量-径流模型进行了校核和验证。拟合优度指标 NSE 值和 R2 值的结果显示在可接受范围内，2005 年分别为 0.745 和 0.764，2007 年分别为 0.715 和 0.883。2005 年、2009 年、2014 年、2017 年和 2021 年的降雨-径流模拟采用了修正的建成指数和 PIA 复合值（MCBI-PIA）。模拟结果表明，NSE 值在 0.484 至 0.851 之间变化，R2 值在 0.519 至 0.894 之间变化，模拟模型的性能在统计学上是可以接受的。这表明所提出的方法可用于估算不同时期土地利用模式的 PIA，并作为 SWMM 雨量-径流模拟的实际 PIA。

{"title":"Improving the estimation approach of percentage of impervious area for the storm water management model — A case study of the Zengwen reservoir watershed, Taiwan","authors":"Chih-Wei Chuang, Ming-Huei Chen, Wen-Yan Zhang","doi":"10.1016/j.rsase.2024.101409","DOIUrl":"10.1016/j.rsase.2024.101409","url":null,"abstract":"<div><div>The Zengwen Reservoir, located within the Zengwen River watershed, is a crucial water supply source in southern Taiwan. Water resources can be estimated using the rainfall-runoff model of the Storm Water Management Model (SWMM). However, the percentage of impervious area (PIA) is one of the significant factors influencing the SWMM. The purpose of this study is to utilize remote sensing imagery to rapidly and accurately estimate land use as PIA for the SWMM rainfall-runoff model. The rainfall-runoff model of SWMM was calibrated and validated based on observed discharge data in 2005 and 2017. The results of goodness-of-fit indicators of NSE value and R<sup>2</sup> value showed in the acceptable range of 0.745, 0.764 in 2005, 0.715, and 0.883 in 2007, respectively. The modified composite of the built-up index and PIA (MCBI-PIA) was used for rainfall-runoff simulation in 2005, 2009, 2014, 2017, and 2021. The simulation results revealed the NSE value varied from 0.484 to 0.851, and the R<sup>2</sup> value between 0.519 and 0.894 which represented a statistically acceptable performance of the simulation model. It indicates that the proposed method can be applied to estimate the PIA for land use patterns during different periods and utilized as the actual PIA for rainfall-runoff simulation with the SWMM.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101409"},"PeriodicalIF":3.8,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142702974","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

Multilayer optimized deep learning model to analyze spectral indices for predicting the condition of rice blast disease 多层优化深度学习模型分析预测稻瘟病病情的光谱指数

IF 3.8 Q2 ENVIRONMENTAL SCIENCES

Remote Sensing Applications-Society and Environment

Pub Date : 2024-11-22 DOI: 10.1016/j.rsase.2024.101394

Shubhajyoti Das , Pritam Bikram , Arindam Biswas , Vimalkumar C. , Parimal Sinha

Rice blast disease is one of the most destructive infectious diseases that affects world food security. Proper monitoring and an accurate decision-making process can assist in disease management strategy. Ground surveys and sampling are the less accurate, expensive, and time-consuming processes that are ineffective to check epidemic. Satellite data-driven approach might be an ideal cost and time-efficient technique that can provide an accurate result due to its revisit across farmland. Temperature variation is a salient feature of this disease trajectory. Hence, land surface temperature can be a cardinal property for disease risk estimation. Spectral indices-based analysis can be more efficient for tracking the disease density. In this study, the MODIS satellite-based Land Surface Temperature (LST) parameter is used to indicate the disease in the field. The indicated risk estimation is also examined using ground truth observation to provide less erroneous labeling. Various spectral combination based remote sensing indices were accumulated to audit the disease states. Remote sensing indices such as Normalized Difference Vegetation Index (NDVI), Soil Adjusted Vegetation Index (SAVI), Enhanced Vegetation Index (EVI), Normalized Difference Moisture Index (NDMI), and Moisture Stress were obtained from the Sentinel-2 archive. These images, depicting the various indices, are processed through a novel optimized deep learning model to predict the disease condition of farmland. The model is developed using various residual networks with

L 2

regularization and batch normalization to enhance the performance of the model. A combination of convolution layers is used to extract crucial spectral information from the remote sensing images and processed through fully connected layers to prognosticate the state of the disease. The model can predict with 89.67% accuracy using the EVI parameters for different geographical positions compared with other remote sensing parameters and has less chance of erroneous possibilities. The proposed system will lead to improved agricultural monitoring management for the incidence of leaf blast disease in real-time.

稻瘟病是影响世界粮食安全的最具破坏性的传染病之一。适当的监测和准确的决策过程有助于制定病害管理策略。地面调查和取样的准确性较低、成本较高、耗时较长，无法有效控制疫情。以卫星数据为驱动的方法可能是一种理想的成本和时间效率高的技术，由于它可以在农田中进行重访，因此可以提供准确的结果。温度变化是这种疾病发生轨迹的一个显著特征。因此，地表温度可以作为疾病风险评估的一个重要属性。基于光谱指数的分析可以更有效地追踪病害密度。在本研究中，基于 MODIS 卫星的地表温度（LST）参数被用来指示田间的病害。此外，还利用地面实况观测数据对指示风险估算进行了检查，以减少错误标记。积累了各种基于光谱组合的遥感指数来审核疾病状态。归一化差异植被指数 (NDVI)、土壤调整植被指数 (SAVI)、增强植被指数 (EVI)、归一化差异水分指数 (NDMI) 和水分压力等遥感指数均来自哨兵 2 号档案。这些描绘各种指数的图像经过新型优化深度学习模型处理后，可预测农田的病害状况。该模型是利用各种残差网络开发的，采用 L2 正则化和批量归一化来提高模型的性能。利用卷积层的组合从遥感图像中提取关键的光谱信息，并通过全连接层进行处理，以预测病害状况。与其他遥感参数相比，该模型使用 EVI 参数对不同地理位置进行预测的准确率高达 89.67%，而且错误概率较低。所提出的系统将有助于改进农业监测管理，实时监测叶瘟的发病情况。

{"title":"Multilayer optimized deep learning model to analyze spectral indices for predicting the condition of rice blast disease","authors":"Shubhajyoti Das , Pritam Bikram , Arindam Biswas , Vimalkumar C. , Parimal Sinha","doi":"10.1016/j.rsase.2024.101394","DOIUrl":"10.1016/j.rsase.2024.101394","url":null,"abstract":"<div><div>Rice blast disease is one of the most destructive infectious diseases that affects world food security. Proper monitoring and an accurate decision-making process can assist in disease management strategy. Ground surveys and sampling are the less accurate, expensive, and time-consuming processes that are ineffective to check epidemic. Satellite data-driven approach might be an ideal cost and time-efficient technique that can provide an accurate result due to its revisit across farmland. Temperature variation is a salient feature of this disease trajectory. Hence, land surface temperature can be a cardinal property for disease risk estimation. Spectral indices-based analysis can be more efficient for tracking the disease density. In this study, the MODIS satellite-based Land Surface Temperature (LST) parameter is used to indicate the disease in the field. The indicated risk estimation is also examined using ground truth observation to provide less erroneous labeling. Various spectral combination based remote sensing indices were accumulated to audit the disease states. Remote sensing indices such as Normalized Difference Vegetation Index (NDVI), Soil Adjusted Vegetation Index (SAVI), Enhanced Vegetation Index (EVI), Normalized Difference Moisture Index (NDMI), and Moisture Stress were obtained from the Sentinel-2 archive. These images, depicting the various indices, are processed through a novel optimized deep learning model to predict the disease condition of farmland. The model is developed using various residual networks with <span><math><mrow><mi>L</mi><mn>2</mn></mrow></math></span> regularization and batch normalization to enhance the performance of the model. A combination of convolution layers is used to extract crucial spectral information from the remote sensing images and processed through fully connected layers to prognosticate the state of the disease. The model can predict with 89.67% accuracy using the EVI parameters for different geographical positions compared with other remote sensing parameters and has less chance of erroneous possibilities. The proposed system will lead to improved agricultural monitoring management for the incidence of leaf blast disease in real-time.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101394"},"PeriodicalIF":3.8,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142702975","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

Spatiotemporal analysis of atmospheric methane concentrations and key influencing factors using machine learning in the Middle East (2010–2021) 利用机器学习对中东地区大气甲烷浓度和主要影响因素进行时空分析（2010-2021 年）

IF 3.8 Q2 ENVIRONMENTAL SCIENCES

Remote Sensing Applications-Society and Environment

Pub Date : 2024-11-20 DOI: 10.1016/j.rsase.2024.101406

Seyed Mohsen Mousavi

Methane (CH₄) is a potent greenhouse gas that significantly impacts climate change due to its rising atmospheric concentrations. Hence, it is crucial to comprehend the spatial and temporal fluctuations in atmospheric CH₄ concentration (XCH₄) at both national and international levels. This study investigates the correlation between atmospheric XCH₄ concentrations (XCH₄) and key influencing factors to identify the primary sources and sinks of CH₄ across the Middle East (ME). Initially, XCH₄ data from the GOSAT satellite, covering the period from 2010 to 2021, were employed to generate spatiotemporal distribution maps of XCH₄ across the ME region. Subsequently, the study investigated the single and simultaneous relationship between XCH₄ and relevant environmental factors, such as vegetation, temperature, precipitation, and others, across different months using correlation analysis and the Permutation Feature Importance (PFI) method to identify the key factors influencing XCH₄ variations. The results reveal significant spatial and temporal variations in XCH₄ concentrations, with higher levels detected in the central and southern regions of the ME during the summer months. The results also highlight the presence of both peak positive and negative correlations with temperature and moisture during winter months. Additionally, both precipitation and vegetation demonstrated negative correlations with XCH₄, especially during the winter and plant-growing seasons. According to the PFI results, temperature emerged as the most significant factor, accounting for over 40% of the variance in XCH₄ concentrations during summer. At the same time, anthropogenic activities exerted minimal influence on these patterns. This comprehensive spatiotemporal analysis provides crucial insights into the variation of CH₄ and its primary drivers in this climatically vulnerable region. Identifying emission patterns can support the development of targeted mitigation policies to curb the future rise of CH₄.

甲烷（CH4）是一种强效温室气体，由于其在大气中的浓度不断上升，对气候变化产生了重大影响。因此，了解国家和国际层面大气中 CH4 浓度（XCH4）的时空波动至关重要。本研究调查了大气中 XCH4 浓度（XCH4）与主要影响因素之间的相关性，以确定中东（ME）地区 CH4 的主要来源和吸收汇。首先，利用 GOSAT 卫星提供的 XCH4 数据生成整个中东地区 XCH4 的时空分布图，时间跨度为 2010 年至 2021 年。随后，研究利用相关性分析和排列特征重要性（PFI）方法，研究了不同月份 XCH4 与植被、温度、降水等相关环境因素之间的单一和同步关系，以确定影响 XCH4 变化的关键因素。结果表明，XCH4浓度存在明显的时空变化，在夏季，地中海中部和南部地区的浓度水平较高。结果还显示，在冬季月份，XCH4 浓度与温度和湿度之间存在正相关和负相关的峰值。此外，降水和植被与 XCH4 呈负相关，尤其是在冬季和植物生长季节。根据 PFI 结果，温度是最重要的因素，占夏季 XCH4 浓度变异的 40% 以上。同时，人为活动对这些模式的影响微乎其微。这项全面的时空分析提供了有关这一气候脆弱地区甲烷变化及其主要驱动因素的重要见解。确定排放模式有助于制定有针对性的减缓政策，以遏制未来甲烷的上升。

{"title":"Spatiotemporal analysis of atmospheric methane concentrations and key influencing factors using machine learning in the Middle East (2010–2021)","authors":"Seyed Mohsen Mousavi","doi":"10.1016/j.rsase.2024.101406","DOIUrl":"10.1016/j.rsase.2024.101406","url":null,"abstract":"<div><div>Methane (CH<sub>4</sub>) is a potent greenhouse gas that significantly impacts climate change due to its rising atmospheric concentrations. Hence, it is crucial to comprehend the spatial and temporal fluctuations in atmospheric CH<sub>4</sub> concentration (XCH<sub>4</sub>) at both national and international levels. This study investigates the correlation between atmospheric XCH<sub>4</sub> concentrations (XCH<sub>4</sub>) and key influencing factors to identify the primary sources and sinks of CH<sub>4</sub> across the Middle East (ME). Initially, XCH<sub>4</sub> data from the GOSAT satellite, covering the period from 2010 to 2021, were employed to generate spatiotemporal distribution maps of XCH<sub>4</sub> across the ME region. Subsequently, the study investigated the single and simultaneous relationship between XCH<sub>4</sub> and relevant environmental factors, such as vegetation, temperature, precipitation, and others, across different months using correlation analysis and the Permutation Feature Importance (PFI) method to identify the key factors influencing XCH<sub>4</sub> variations. The results reveal significant spatial and temporal variations in XCH<sub>4</sub> concentrations, with higher levels detected in the central and southern regions of the ME during the summer months. The results also highlight the presence of both peak positive and negative correlations with temperature and moisture during winter months. Additionally, both precipitation and vegetation demonstrated negative correlations with XCH<sub>4</sub>, especially during the winter and plant-growing seasons. According to the PFI results, temperature emerged as the most significant factor, accounting for over 40% of the variance in XCH<sub>4</sub> concentrations during summer. At the same time, anthropogenic activities exerted minimal influence on these patterns. This comprehensive spatiotemporal analysis provides crucial insights into the variation of CH<sub>4</sub> and its primary drivers in this climatically vulnerable region. Identifying emission patterns can support the development of targeted mitigation policies to curb the future rise of CH<sub>4</sub>.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101406"},"PeriodicalIF":3.8,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142720418","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

Examining the nexus of social vulnerability, land cover dynamics, and heat exposure in Reno, Nevada, USA 研究美国内华达州里诺市社会脆弱性、土地覆被动态和热暴露之间的关系

IF 3.8 Q2 ENVIRONMENTAL SCIENCES

Remote Sensing Applications-Society and Environment

Pub Date : 2024-11-20 DOI: 10.1016/j.rsase.2024.101400

Consolata Wangechi Macharia, Lawrence Kiage

Intense heat is a persistent urban challenge whose impacts are detrimental to human health. Heat-related effects disproportionately impact underserved populations. Modification of urban landscapes through increased imperviousness intensifies surface temperatures, leading to heightened heat exposure risks. While climate adaptation efforts have advanced, they are inadequate in addressing the uncertainties of climate change and the long-term risks of climate-related hazards. In addition, despite the numerous heat vulnerability studies across U.S. cities, the City of Reno is largely understudied. To address these gaps, the research examined the relationship between the spatiotemporal patterns of social vulnerability, changes in biophysical properties, and the heat hazard in Reno, Nevada. We utilized CDC census data to map the Social Vulnerability Index (SVI) and Landsat satellite data from 1990 to 2023 to analyze Land Surface Temperature (LST) trends for a temporal comparative study of heat patterns. Additionally, we employed the Normalized Difference Vegetation Index (NDVI) for vegetation extent. The zonal statistics tool helped assess the influence of different land use features on surface temperatures. The results showed that regions identified as social vulnerability hotspots often coincided with areas highly exposed to extreme temperatures and vice versa. Our findings also revealed an extension of heat vulnerability hotspots from the urban core to suburban regions. We observed a decline in mean LST values in regions covered by vegetation and a rise in mean surface temperatures in regions encompassed with imperviousness. These findings underscore the need for increased vegetation for heat mitigation.

酷热是一个持续存在的城市挑战，其影响有损人类健康。与高温相关的影响对得不到充分服务的人群造成了不成比例的影响。通过增加不透水率对城市景观进行改造，加剧了地表温度，导致热暴露风险增加。虽然适应气候的努力取得了进展，但这些努力不足以应对气候变化的不确定性以及与气候相关的危害的长期风险。此外，尽管对美国各城市的高温脆弱性进行了大量研究，但对里诺市的研究大多不足。为了填补这些空白，本研究考察了内华达州里诺市的社会脆弱性时空模式、生物物理特性变化和高温危害之间的关系。我们利用疾病预防控制中心的人口普查数据绘制了社会脆弱性指数 (SVI) 图，并利用 1990 年至 2023 年的 Landsat 卫星数据分析了陆地表面温度 (LST) 趋势，从而对热模式进行了时空比较研究。此外，我们还采用归一化差异植被指数（NDVI）分析植被范围。分区统计工具有助于评估不同土地利用特征对地表温度的影响。结果表明，被确定为社会脆弱性热点的地区往往与受极端气温影响较大的地区重合，反之亦然。我们的研究结果还揭示了热脆弱性热点从城市核心地区向郊区的延伸。我们观察到植被覆盖地区的平均 LST 值下降，而不透水地区的平均地表温度上升。这些发现强调了增加植被以缓解高温的必要性。

{"title":"Examining the nexus of social vulnerability, land cover dynamics, and heat exposure in Reno, Nevada, USA","authors":"Consolata Wangechi Macharia, Lawrence Kiage","doi":"10.1016/j.rsase.2024.101400","DOIUrl":"10.1016/j.rsase.2024.101400","url":null,"abstract":"<div><div>Intense heat is a persistent urban challenge whose impacts are detrimental to human health. Heat-related effects disproportionately impact underserved populations. Modification of urban landscapes through increased imperviousness intensifies surface temperatures, leading to heightened heat exposure risks. While climate adaptation efforts have advanced, they are inadequate in addressing the uncertainties of climate change and the long-term risks of climate-related hazards. In addition, despite the numerous heat vulnerability studies across U.S. cities, the City of Reno is largely understudied. To address these gaps, the research examined the relationship between the spatiotemporal patterns of social vulnerability, changes in biophysical properties, and the heat hazard in Reno, Nevada. We utilized CDC census data to map the Social Vulnerability Index (SVI) and Landsat satellite data from 1990 to 2023 to analyze Land Surface Temperature (LST) trends for a temporal comparative study of heat patterns. Additionally, we employed the Normalized Difference Vegetation Index (NDVI) for vegetation extent. The zonal statistics tool helped assess the influence of different land use features on surface temperatures. The results showed that regions identified as social vulnerability hotspots often coincided with areas highly exposed to extreme temperatures and vice versa. Our findings also revealed an extension of heat vulnerability hotspots from the urban core to suburban regions. We observed a decline in mean LST values in regions covered by vegetation and a rise in mean surface temperatures in regions encompassed with imperviousness. These findings underscore the need for increased vegetation for heat mitigation.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101400"},"PeriodicalIF":3.8,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142720417","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

Integrated multi-satellite data and machine learning approach in mapping the successional stages of forest types in a tropical montane forest 综合多卫星数据和机器学习方法在热带山地森林类型演替阶段制图中的应用

IF 3.8 Q2 ENVIRONMENTAL SCIENCES

Remote Sensing Applications-Society and Environment

Pub Date : 2024-11-20 DOI: 10.1016/j.rsase.2024.101407

Richard Dein D. Altarez , Armando Apan , Tek Maraseni

Understanding the successional stages in tropical montane forests (TMF) is crucial for its conservation and management. This study integrated Sentinel-1, Sentinel-2, InSAR, GEDI, and machine learning to map the categorical successional stages of different forest types in a Philippines’ TMF. Field data collected from December 2022 to January 2023 were used to create and validate successional stages models. Sentinel-1 interferogram, unwrapped interferogram, and coherence exhibited moderate positive correlations with canopy height (r = 0.43). Incorporating GEDI with InSAR to predict canopy height yielded less accurate predictions (r = −0.20 to 0.04; RMSE = 12–13 m). Results show that canopy height, a widely accepted attribute for forest structure, appears secondary to other biophysical variables. Integrating optical, radar, and auxiliary variables achieved an overall accuracy of 79.56% and a kappa value of 75.74%. Feature importance analysis using Random Forest enhanced the overall accuracy (84.22%) and kappa value (81.19%). The integration of multi-satellite data with machine learning has proven effective for studying TMFs successional stages. Elevation emerged as the most significant predictor of forest type distribution, with mature and young pine forests dominating lower elevation (700–1,400m) and mossy forests dominating above 1,400m. Given the observed disturbances, the study underscores the need for robust conservation strategies and sustainable TMF management. Future research should focus on time-series analyses of successional stages, further optimization of machine learning models, and integrating additional data sources, such as LiDAR, to enhance canopy height predictions and forest monitoring efforts. The findings also provide valuable knowledge applicable to TMFs globally, supporting informed conservation and policies intended to protect biodiversity.

了解热带山地森林演替阶段对其保护和管理具有重要意义。该研究综合了Sentinel-1、Sentinel-2、InSAR、GEDI和机器学习，绘制了菲律宾TMF不同森林类型的分类演替阶段。从2022年12月到2023年1月收集的现场数据用于创建和验证连续阶段模型。Sentinel-1干涉图、未包裹干涉图和相干性与冠层高度呈中等正相关（r = 0.43）。结合GEDI和InSAR预测冠层高度的准确度较低(r = - 0.20 ~ 0.04；研究结果表明，林冠高度作为森林结构的一个被广泛接受的属性，其重要性次于其他生物物理变量。综合光学、雷达和辅助变量，总体精度为79.56%，kappa值为75.74%。随机森林特征重要性分析提高了总体准确率（84.22%）和kappa值（81.19%）。多卫星数据与机器学习相结合已被证明是研究TMFs连续阶段的有效方法。海拔是森林类型分布最显著的预测因子，低海拔（700 - 1400米）以成熟和幼松林为主，1400米以上以苔藓林为主。鉴于观察到的干扰，该研究强调了强有力的保护策略和可持续的TMF管理的必要性。未来的研究应侧重于演代阶段的时间序列分析，进一步优化机器学习模型，并整合其他数据源，如激光雷达，以加强冠层高度预测和森林监测工作。研究结果还提供了适用于全球TMFs的宝贵知识，支持旨在保护生物多样性的知情保护和政策。

{"title":"Integrated multi-satellite data and machine learning approach in mapping the successional stages of forest types in a tropical montane forest","authors":"Richard Dein D. Altarez , Armando Apan , Tek Maraseni","doi":"10.1016/j.rsase.2024.101407","DOIUrl":"10.1016/j.rsase.2024.101407","url":null,"abstract":"<div><div>Understanding the successional stages in tropical montane forests (TMF) is crucial for its conservation and management. This study integrated Sentinel-1, Sentinel-2, InSAR, GEDI, and machine learning to map the categorical successional stages of different forest types in a Philippines’ TMF. Field data collected from December 2022 to January 2023 were used to create and validate successional stages models. Sentinel-1 interferogram, unwrapped interferogram, and coherence exhibited moderate positive correlations with canopy height (r = 0.43). Incorporating GEDI with InSAR to predict canopy height yielded less accurate predictions (r = −0.20 to 0.04; RMSE = 12–13 m). Results show that canopy height, a widely accepted attribute for forest structure, appears secondary to other biophysical variables. Integrating optical, radar, and auxiliary variables achieved an overall accuracy of 79.56% and a kappa value of 75.74%. Feature importance analysis using Random Forest enhanced the overall accuracy (84.22%) and kappa value (81.19%). The integration of multi-satellite data with machine learning has proven effective for studying TMFs successional stages. Elevation emerged as the most significant predictor of forest type distribution, with mature and young pine forests dominating lower elevation (700–1,400m) and mossy forests dominating above 1,400m. Given the observed disturbances, the study underscores the need for robust conservation strategies and sustainable TMF management. Future research should focus on time-series analyses of successional stages, further optimization of machine learning models, and integrating additional data sources, such as LiDAR, to enhance canopy height predictions and forest monitoring efforts. The findings also provide valuable knowledge applicable to TMFs globally, supporting informed conservation and policies intended to protect biodiversity.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101407"},"PeriodicalIF":3.8,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142748003","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A review of the global operational geostationary meteorological satellites 全球实用地球静止气象卫星回顾

IF 3.8 Q2 ENVIRONMENTAL SCIENCES

Remote Sensing Applications-Society and Environment

Pub Date : 2024-11-20 DOI: 10.1016/j.rsase.2024.101403

Ram Kumar Giri , Satya Prakash , Ramashray Yadav , Nitesh Kaushik , Munn Vinayak Shukla , P.K. Thapliyal , K.C. Saikrishnan

Geostationary meteorological satellite data and products are proven to be indispensable in operational weather monitoring and forecasting for various sectorial applications and disaster risk reduction due to their large spatial coverage and spatio-temporally consistent availability. The meteorological instruments such as imager or radiometer and atmospheric sounder onboard these satellites have gone through incremental advancement in terms of accuracy, stability, and resolutions. In addition, new meteorological instruments such as lightning detection and ocean monitoring payloads have been developed in the recent decades. This paper reviews brief history of the global operational geostationary meteorological satellites and onboard meteorological instruments. The capability of currently available operational geostationary meteorological satellites is also highlighted. In order to prepare a global climate data record of geostationary satellite observations, well-calibrated data are essentially required from each operational satellite. The calibration exercises taken up by several satellite agencies under the Global Space-based Inter-Calibration System, and development of global and regional long-term inter-calibrated geostationary climate data records are briefly discussed. Moreover, expected meteorological instruments onboard the proposed next-generation geostationary satellites from different satellite agencies across the globe are summarized.

地球静止气象卫星数据和产品因其空间覆盖面大和时空一致性强，已被证明是各行业应用和减少灾害风险的业务天气监测和预报所不可或缺的。这些卫星上搭载的气象仪器，如成像仪或辐射计和大气探测仪，在精度、稳定性和分辨率方面都有逐步提高。此外，近几十年来还开发了新的气象仪器，如闪电探测和海洋监测有效载荷。本文简要回顾了全球业务地球静止气象卫星和星载气象仪器的历史。本文还重点介绍了现有业务地球静止气象卫星的能力。为了编制地球静止卫星观测的全球气候数据记录，基本上需要每颗业务卫星提供经过良好校准的数据。简要讨论了几个卫星机构在全球天基相互校准系统下开展的校准工作，以及全球和区域长期相互校准地球静止气候数据记录的编制工作。此外，还概述了全球不同卫星机构预计在拟议的下一代地球静止卫星上安装的气象仪器。

{"title":"A review of the global operational geostationary meteorological satellites","authors":"Ram Kumar Giri , Satya Prakash , Ramashray Yadav , Nitesh Kaushik , Munn Vinayak Shukla , P.K. Thapliyal , K.C. Saikrishnan","doi":"10.1016/j.rsase.2024.101403","DOIUrl":"10.1016/j.rsase.2024.101403","url":null,"abstract":"<div><div>Geostationary meteorological satellite data and products are proven to be indispensable in operational weather monitoring and forecasting for various sectorial applications and disaster risk reduction due to their large spatial coverage and spatio-temporally consistent availability. The meteorological instruments such as imager or radiometer and atmospheric sounder onboard these satellites have gone through incremental advancement in terms of accuracy, stability, and resolutions. In addition, new meteorological instruments such as lightning detection and ocean monitoring payloads have been developed in the recent decades. This paper reviews brief history of the global operational geostationary meteorological satellites and onboard meteorological instruments. The capability of currently available operational geostationary meteorological satellites is also highlighted. In order to prepare a global climate data record of geostationary satellite observations, well-calibrated data are essentially required from each operational satellite. The calibration exercises taken up by several satellite agencies under the Global Space-based Inter-Calibration System, and development of global and regional long-term inter-calibrated geostationary climate data records are briefly discussed. Moreover, expected meteorological instruments onboard the proposed next-generation geostationary satellites from different satellite agencies across the globe are summarized.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101403"},"PeriodicalIF":3.8,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142703690","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

Analysis of spatiotemporal surface water variability and drought conditions using remote sensing indices in the Kagera River Sub-Basin, Tanzania 利用遥感指数分析坦桑尼亚卡盖拉河分流域地表水的时空变化和干旱状况

IF 3.8 Q2 ENVIRONMENTAL SCIENCES

Remote Sensing Applications-Society and Environment

Pub Date : 2024-11-19 DOI: 10.1016/j.rsase.2024.101405

Nickson Tibangayuka , Deogratias M.M. Mulungu , Fides Izdori

Drought is one of the major challenges affecting water resources, agriculture, and ecosystem resilience in the sub-Saharan region. This study analyzed the spatial and temporal variation of surface water and drought conditions in the Kagera sub-basin using remote sensing indices: the Normalized Difference Water Index (NDWI), Normalized Difference Vegetation Index (NDVI), Soil Adjusted Vegetation Index (SAVI), and Normalized Difference Moisture Index (NDMI). The analysis covered the period from 1985 to 2020 at 5-year intervals. The Standardized Precipitation Index (SPI) was utilized to assess rainfall anomalies, which were then compared with surface water variability and drought intensity indicated by remote-sensing indices. The SPI revealed multiple instances of extreme and severe drought, with higher frequencies observed in the 3-month and 6-month SPI compared to the 12-month SPI. The NDWI revealed significant spatial and temporal variations in surface water area in the Kagera sub-basin. In general, surface water area showed a mixed trend, decreasing from 660 km² in 1985 to 632 km² in 2000, and then gradually increasing to 698 km² in 2020. Additionally, the NDWI exhibited a strong correlation with 3-month and 6-month SPI but a weaker correlation with 12-month SPI. On the other hand, the NDVI indicated significant variations in drought conditions, with areas experiencing severe drought ranging between 446 km² and 1892 km². These severe drought events were prevalent from 1990 to 2000. The results also indicated a strong correlation between drought extent and intensity extracted from NDVI and rainfall anomalies, with SPI-3 and SPI-6 showing stronger correlations compared to SPI-12. Moreover, the SAVI results were consistent with those of NDVI, suggesting that the soil brightness effect on the NDVI is not significant in the sub-basin. In contrast, NDMI indicated that severe drought areas generally increased over the analyzed years and exhibited a weak correlation with SPI for all time scales. These findings contribute valuable insights that are important for decision-makers in managing surface water resources and implementing proactive and targeted environmental conservation measures to enhance ecosystem resilience in the Kagera sub-basin.

干旱是影响撒哈拉以南地区水资源、农业和生态系统恢复能力的主要挑战之一。本研究利用遥感指数：归一化差异水指数（NDWI）、归一化差异植被指数（NDVI）、土壤调整植被指数（SAVI）和归一化差异水分指数（NDMI），分析了卡盖拉亚盆地地表水和干旱状况的时空变化。分析时间跨度为 1985 年至 2020 年，间隔为 5 年。利用标准化降水指数（SPI）评估降雨异常，然后与遥感指数显示的地表水变化和干旱强度进行比较。SPI 显示了多种极端和严重干旱的情况，与 12 个月的 SPI 相比，3 个月和 6 个月的 SPI 观察到的频率更高。NDWI 显示，卡盖拉分流域的地表水面积存在显著的时空变化。总体而言，地表水面积呈混合趋势，从 1985 年的 660 平方公里减少到 2000 年的 632 平方公里，然后逐渐增加到 2020 年的 698 平方公里。此外，NDWI 与 3 个月和 6 个月 SPI 的相关性较强，但与 12 个月 SPI 的相关性较弱。另一方面，归一化差异植被指数（NDVI）显示出干旱状况的显著变化，发生严重干旱的面积在 446 平方公里到 1892 平方公里之间。这些严重干旱事件主要发生在 1990 年至 2000 年期间。结果还表明，从 NDVI 和降雨异常中提取的干旱范围和强度之间存在很强的相关性，与 SPI-12 相比，SPI-3 和 SPI-6 显示出更强的相关性。此外，SAVI 的结果与 NDVI 的结果一致，表明该子流域的土壤亮度对 NDVI 的影响不大。相比之下，NDMI 表明严重干旱地区在分析年份普遍增加，并且在所有时间尺度上与 SPI 的相关性较弱。这些发现提供了宝贵的见解，对决策者管理地表水资源、实施积极主动和有针对性的环境保护措施以提高卡盖拉亚流域生态系统的恢复能力非常重要。

{"title":"Analysis of spatiotemporal surface water variability and drought conditions using remote sensing indices in the Kagera River Sub-Basin, Tanzania","authors":"Nickson Tibangayuka , Deogratias M.M. Mulungu , Fides Izdori","doi":"10.1016/j.rsase.2024.101405","DOIUrl":"10.1016/j.rsase.2024.101405","url":null,"abstract":"<div><div>Drought is one of the major challenges affecting water resources, agriculture, and ecosystem resilience in the sub-Saharan region. This study analyzed the spatial and temporal variation of surface water and drought conditions in the Kagera sub-basin using remote sensing indices: the Normalized Difference Water Index (NDWI), Normalized Difference Vegetation Index (NDVI), Soil Adjusted Vegetation Index (SAVI), and Normalized Difference Moisture Index (NDMI). The analysis covered the period from 1985 to 2020 at 5-year intervals. The Standardized Precipitation Index (SPI) was utilized to assess rainfall anomalies, which were then compared with surface water variability and drought intensity indicated by remote-sensing indices. The SPI revealed multiple instances of extreme and severe drought, with higher frequencies observed in the 3-month and 6-month SPI compared to the 12-month SPI. The NDWI revealed significant spatial and temporal variations in surface water area in the Kagera sub-basin. In general, surface water area showed a mixed trend, decreasing from 660 km<sup>2</sup> in 1985 to 632 km<sup>2</sup> in 2000, and then gradually increasing to 698 km<sup>2</sup> in 2020. Additionally, the NDWI exhibited a strong correlation with 3-month and 6-month SPI but a weaker correlation with 12-month SPI. On the other hand, the NDVI indicated significant variations in drought conditions, with areas experiencing severe drought ranging between 446 km<sup>2</sup> and 1892 km<sup>2</sup>. These severe drought events were prevalent from 1990 to 2000. The results also indicated a strong correlation between drought extent and intensity extracted from NDVI and rainfall anomalies, with SPI-3 and SPI-6 showing stronger correlations compared to SPI-12. Moreover, the SAVI results were consistent with those of NDVI, suggesting that the soil brightness effect on the NDVI is not significant in the sub-basin. In contrast, NDMI indicated that severe drought areas generally increased over the analyzed years and exhibited a weak correlation with SPI for all time scales. These findings contribute valuable insights that are important for decision-makers in managing surface water resources and implementing proactive and targeted environmental conservation measures to enhance ecosystem resilience in the Kagera sub-basin.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101405"},"PeriodicalIF":3.8,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142703692","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

Assessing drivers of vegetation fire occurrence in Zimbabwe - Insights from Maxent modelling and historical data analysis 评估津巴布韦植被火灾发生的驱动因素--Maxent 建模和历史数据分析的启示

IF 3.8 Q2 ENVIRONMENTAL SCIENCES

Remote Sensing Applications-Society and Environment

Pub Date : 2024-11-19 DOI: 10.1016/j.rsase.2024.101404

Upenyu Mupfiga , Onisimo Mutanga , Timothy Dube

Vegetation fires are known to profoundly impact ecosystem structure and composition, posing threats to ecosystem stability and human safety. In Zimbabwe, uncontrolled fires have been recurrent, yet a rigorous analysis of the key drivers is still lacking. Previous studies in Zimbabwe have predominantly focused on spatio-temporal dynamics of the occurrence of vegetation fire, leaving a gap in understanding the underlying drivers. Accurate prediction of fire occurrence and identification of the major drivers is imperative for effective fire management strategies. The study employs the Maxent model, a machine-learning approach, to analyze historical MODIS fire data alongside bioclimatic, topographic, anthropogenic, and vegetation variables, to assess the likelihood of fire occurrence in Zimbabwe. The research also aims to elucidate the major factors that influence fire occurrence within the region. The independent contributions of predictor variables to the model's goodness of fit are evaluated using a jackknife test, while model accuracy is assessed using the AUC (area under the receiver operating characteristic curve). Results indicate that elevation, precipitation seasonality, temperature annual range and human footprint emerge as the major factors influencing fire occurrence in Zimbabwe. The model demonstrates an acceptable accuracy, with an average AUC of 0.77. This study underscores the utility of the Maxent model in elucidating the contributions of various environmental factors to vegetation fire occurrence. Moreover, the ability of the model to predict the probability of fire occurrence offers valuable insights for fire managers, facilitating the assessment of the spatial vulnerability of vegetation to fire occurrence. Overall, this research contributes to an improved understanding of the drivers of vegetation fires in Zimbabwe and provides a practical tool for enhancing fire management efforts in the region and beyond.

众所周知，植被火灾会严重影响生态系统结构和组成，对生态系统的稳定性和人类安全构成威胁。在津巴布韦，不受控制的火灾屡屡发生，但仍缺乏对其关键驱动因素的严谨分析。以前在津巴布韦进行的研究主要集中在植被火灾发生的时空动态方面，对其根本原因的认识还存在差距。要制定有效的火灾管理策略，就必须准确预测火灾的发生并找出主要驱动因素。本研究采用机器学习方法 Maxent 模型分析 MODIS 历史火灾数据以及生物气候、地形、人为和植被变量，以评估津巴布韦发生火灾的可能性。研究还旨在阐明影响该地区火灾发生的主要因素。预测变量对模型拟合度的独立贡献采用千斤顶检验法进行评估，而模型的准确性则采用 AUC（接收器工作特征曲线下面积）进行评估。结果表明，海拔高度、降水季节性、气温年变化范围和人类足迹是影响津巴布韦火灾发生的主要因素。该模型的准确性尚可接受，平均 AUC 为 0.77。这项研究强调了 Maxent 模型在阐明各种环境因素对植被火灾发生的影响方面的实用性。此外，该模型预测火灾发生概率的能力为火灾管理者提供了宝贵的见解，有助于评估植被在空间上对火灾发生的脆弱性。总之，这项研究有助于更好地了解津巴布韦植被火灾的驱动因素，并为加强该地区及其他地区的火灾管理工作提供了实用工具。

{"title":"Assessing drivers of vegetation fire occurrence in Zimbabwe - Insights from Maxent modelling and historical data analysis","authors":"Upenyu Mupfiga , Onisimo Mutanga , Timothy Dube","doi":"10.1016/j.rsase.2024.101404","DOIUrl":"10.1016/j.rsase.2024.101404","url":null,"abstract":"<div><div>Vegetation fires are known to profoundly impact ecosystem structure and composition, posing threats to ecosystem stability and human safety. In Zimbabwe, uncontrolled fires have been recurrent, yet a rigorous analysis of the key drivers is still lacking. Previous studies in Zimbabwe have predominantly focused on spatio-temporal dynamics of the occurrence of vegetation fire, leaving a gap in understanding the underlying drivers. Accurate prediction of fire occurrence and identification of the major drivers is imperative for effective fire management strategies. The study employs the Maxent model, a machine-learning approach, to analyze historical MODIS fire data alongside bioclimatic, topographic, anthropogenic, and vegetation variables, to assess the likelihood of fire occurrence in Zimbabwe. The research also aims to elucidate the major factors that influence fire occurrence within the region. The independent contributions of predictor variables to the model's goodness of fit are evaluated using a jackknife test, while model accuracy is assessed using the AUC (area under the receiver operating characteristic curve). Results indicate that elevation, precipitation seasonality, temperature annual range and human footprint emerge as the major factors influencing fire occurrence in Zimbabwe. The model demonstrates an acceptable accuracy, with an average AUC of 0.77. This study underscores the utility of the Maxent model in elucidating the contributions of various environmental factors to vegetation fire occurrence. Moreover, the ability of the model to predict the probability of fire occurrence offers valuable insights for fire managers, facilitating the assessment of the spatial vulnerability of vegetation to fire occurrence. Overall, this research contributes to an improved understanding of the drivers of vegetation fires in Zimbabwe and provides a practical tool for enhancing fire management efforts in the region and beyond.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101404"},"PeriodicalIF":3.8,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142702973","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A novel spatio-temporal vision transformer model for improving wetland mapping using multi-seasonal sentinel data 利用多季节哨点数据改进湿地绘图的新型时空视觉转换器模型

IF 3.8 Q2 ENVIRONMENTAL SCIENCES

Remote Sensing Applications-Society and Environment

Pub Date : 2024-11-17 DOI: 10.1016/j.rsase.2024.101401

Mohammad Marjani , Fariba Mohammadimanesh , Masoud Mahdianpari , Eric W. Gill

Wetlands mapping using remote sensing data is a challenging task due to the spectral similarity of wetlands, the fragmented nature of these landscapes, and seasonal variations in wetlands. To address these limitations, this study proposes a novel spatio-temporal vision transformer (ST-ViT) model for an accurate wetland classification using seasonal data. The ST-ViT model was trained using multi-seasonal Sentinel-1 (S1) and Sentinel-2 (S2) data acquired during the spring, summer, and fall of 2020 in a study area located in Newfoundland and Labrador, Canada. The performance of the ST-ViT model was evaluated against the validation dataset, achieving an overall accuracy (OA) of 0.950 and F1-score (F1) of 0.934, outperforming other deep learning models such as random forest (RF), hybrid spectral network (HybridSN), etc. The model demonstrated strong classification capabilities among most wetland classes, with some challenges in distinguishing between spectrally similar classes like bogs and fens. Moreover, the integration of spatio-temporal features enabled the reduction of feature mixing between wetland classes, particularly during different seasons. The ST-ViT model provides an accurate wetland distribution map in different seasons, supporting critical decision-making processes related to wetland conservation and environmental monitoring.

由于湿地的光谱相似性、这些景观的破碎性以及湿地的季节性变化，使用遥感数据绘制湿地地图是一项具有挑战性的任务。针对这些局限性，本研究提出了一种新颖的时空视觉转换器（ST-ViT）模型，用于利用季节性数据进行准确的湿地分类。ST-ViT 模型是利用 2020 年春季、夏季和秋季在加拿大纽芬兰和拉布拉多研究区域采集的多季节哨兵-1（S1）和哨兵-2（S2）数据进行训练的。根据验证数据集评估了 ST-ViT 模型的性能，其总体准确率（OA）达到 0.950，F1 分数（F1）达到 0.934，优于随机森林（RF）、混合光谱网络（HybridSN）等其他深度学习模型。该模型在大多数湿地类别中都表现出很强的分类能力，但在区分沼泽和沼泽等光谱相似的类别方面存在一些挑战。此外，时空特征的整合减少了湿地类别之间的特征混合，尤其是在不同季节。ST-ViT 模型提供了不同季节的精确湿地分布图，支持与湿地保护和环境监测相关的重要决策过程。

{"title":"A novel spatio-temporal vision transformer model for improving wetland mapping using multi-seasonal sentinel data","authors":"Mohammad Marjani , Fariba Mohammadimanesh , Masoud Mahdianpari , Eric W. Gill","doi":"10.1016/j.rsase.2024.101401","DOIUrl":"10.1016/j.rsase.2024.101401","url":null,"abstract":"<div><div>Wetlands mapping using remote sensing data is a challenging task due to the spectral similarity of wetlands, the fragmented nature of these landscapes, and seasonal variations in wetlands. To address these limitations, this study proposes a novel spatio-temporal vision transformer (ST-ViT) model for an accurate wetland classification using seasonal data. The ST-ViT model was trained using multi-seasonal Sentinel-1 (S1) and Sentinel-2 (S2) data acquired during the spring, summer, and fall of 2020 in a study area located in Newfoundland and Labrador, Canada. The performance of the ST-ViT model was evaluated against the validation dataset, achieving an overall accuracy (OA) of 0.950 and F1-score (F1) of 0.934, outperforming other deep learning models such as random forest (RF), hybrid spectral network (HybridSN), etc. The model demonstrated strong classification capabilities among most wetland classes, with some challenges in distinguishing between spectrally similar classes like bogs and fens. Moreover, the integration of spatio-temporal features enabled the reduction of feature mixing between wetland classes, particularly during different seasons. The ST-ViT model provides an accurate wetland distribution map in different seasons, supporting critical decision-making processes related to wetland conservation and environmental monitoring.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"37 ","pages":"Article 101401"},"PeriodicalIF":3.8,"publicationDate":"2024-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142703691","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