International journal of applied earth observation and geoinformation : ITC journal最新文献

{"title":"Accurate estimation of grain number per panicle in winter wheat by synergistic use of UAV imagery and meteorological data","authors":"Yapeng Wu,&nbsp;Weiguo Yu,&nbsp;Yangyang Gu,&nbsp;Qi Zhang,&nbsp;Yuan Xiong,&nbsp;Hengbiao Zheng,&nbsp;Chongya Jiang,&nbsp;Xia Yao,&nbsp;Yan Zhu,&nbsp;Weixing Cao,&nbsp;Tao Cheng","doi":"10.1016/j.jag.2024.104320","DOIUrl":"10.1016/j.jag.2024.104320","url":null,"abstract":"<div><div>Rapid, accurate, and nondestructive estimation of grain number per panicle (GNPP) in winter wheat is crucial to accelerate smart breeding, improve precision crop management, and ensure food security. As two (panicle number per unit ground area and GNPP) of three commonly used yield components, GNPP was much less quantified with remotely sensed data than the former through visual counting. The limited research suffered from either low accuracies with ground canopy spectra or low efficiency with proximal panicle imaging systems. No studies have been reported on estimating GNPP with unmanned aerial vehicle (UAV) imagery, underscoring its strong advantages in high-resolution and efficient monitoring. To address these issues, this study proposed a practical approach for estimating GNPP in winter wheat by integrating UAV imagery and meteorological data with <em>meta</em>-learning ensemble regression. The potential contributions of different variables were examined for understanding the improvement in the spectral estimation of GNPP, including spectral indices (SIs), the optimal canopy height (CH) metric, and absorbed photosynthetic active radiation (APAR).</div><div>The results demonstrated that CH_P99 (CH at the 99th percentile in the region of interest) derived from red-green-blue (RGB) imagery exhibited the strongest correlation with measured plant height among all RGB- or multispectral (MS)-derived CH metrics. The incorporation of remotely sensed APAR and RGB-derived CH_P99 improved the accuracy of GNPP estimation over using merely color indices or SIs. Among all feature combinations, Comb. #6 (SIs + APAR_MS + CH_P99) yielded the highest overall accuracies in estimating GNPP for individual and multiple stages. Compared with the best anthesis models for Combs. #5–7 (<em>R_val</em>² = 0.52–0.64, RMSE = 2.85–2.47, RRMSE = 6.01–5.21 %), the multi-stage (heading + anthesis) models exhibited higher accuracies in independent validation (<em>R_val</em>² = 0.60–0.65, RMSE = 2.60–2.42, RRMSE = 5.48–5.10 %). The findings suggest this study has opened a new avenue for estimating GNPP with UAV remote sensing. The proposed method for the synergistic use of UAV imagery and meteorological data has great potential in the prediction of GNPP and grain yield over various regions with satellite imagery and climate datasets.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"136 ","pages":"Article 104320"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142874817","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}

{"title":"Low-variance estimation of live fuel moisture content using VIIRS data through radiative transfer model","authors":"Shuai Yang,&nbsp;Rui Chen,&nbsp;Binbin He,&nbsp;Yiru Zhang","doi":"10.1016/j.jag.2024.104311","DOIUrl":"10.1016/j.jag.2024.104311","url":null,"abstract":"<div><div>The Canopy Live Fuel Moisture Content (LFMC) is a pivotal factor in wildfire risk assessment within the fire triangle model, representing the ratio of canopy moisture content to its dry weight. Against the backdrop of degraded Moderate Resolution Imaging Spectroradiometer (MODIS) performance and the underutilization of Visible Infrared Imaging Radiometer Suite (VIIRS) in LFMC inversion, this study harnessed the coupled radiative transfer models (RTMs) to probe the spectral sensitivity of the VIIRS to LFMC and pinpoint the optimal band combination for LFMC inversion. To tackle the challenge of ill-posed inversion, we leveraged the correlation coefficient matrix to mitigate erroneous combinations of free parameters in the construction of the lookup table. Results showcase that VIIRS-based LFMC inversion yields marginally superior accuracy (R<span><math><mrow><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup><mo>=</mo></mrow></math></span> 0.57, R<span><math><mrow><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup><mo>=</mo></mrow></math></span> 0.32) for both grassland and forest types, with VIIRS-based inversion demonstrating a lower relative root mean square error (rRMSE <span><math><mo>=</mo></math></span> 5.84%), compared to results from the MODIS. By scrutinizing LFMC trends alongside precipitation (PP) data in four forest fires spanning from 2019 to 2022 in southwest China, varied degrees of LFMC decrease preceding fire outbreaks. Those results substantiated the validity of the proposed method for wildfire warning. Consequently, our study asserts the reliability of VIIRS in LFMC inversion, positioning it as a viable substitute and extension of MODIS. VIIRS offers continuous and effective product support for wildfire warning assessment, enhancing our ability to monitor and mitigate wildfire risks.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"136 ","pages":"Article 104311"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142874818","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}

{"title":"Integrating RS data with fuzzy decision systems for innovative crop water needs assessment","authors":"Faezeh Sadat Hashemi ,&nbsp;Mohammad Javad Valadan Zoej ,&nbsp;Fahimeh Youssefi ,&nbsp;Huxiong Li ,&nbsp;Sanaz Shafian ,&nbsp;Mahdi Farnaghi ,&nbsp;Saied Pirasteh","doi":"10.1016/j.jag.2024.104338","DOIUrl":"10.1016/j.jag.2024.104338","url":null,"abstract":"<div><div>Irrigation is a critical component of global water usage, accounting for approximately 70 % of water consumption. As the world’s population continues to grow, the demand for food will increase, making it essential to improve irrigation management by reducing water waste and increasing efficiency. This study aims to develop and validate a fuzzy decision-making system that determines crop irrigation needs based on parameters that affect plant water requirements. These parameters can be monitored using Remote sensing (RS) satellites, enabling large-scale agricultural irrigation monitoring. The study utilized Landsat-8 satellite data and meteorological data. It also employed a fuzzy decision system with inputs of estimated evapotranspiration, Normalized Difference Vegetation Index (NDVI), Leaf Area Index (LAI), Land Surface Temperature (LST), Crop Water Stress Index (CWSI), Stress Index (SI), and Soil Moisture (SM). The output of the fuzzy model is a map that effectively determines the irrigation requirements for agricultural land relatively. The system was tested on six Landsat images of winter wheat crops in Tehran University’s agricultural fields. The estimated evapotranspiration was compared to Reference Evapotranspiration (ET_r) obtained from the FAO-Penman-Monteith equation, resulting in a root mean square error of 0.33 mm. The fuzzy decision system was evaluated by comparing its results with Vegetation Water Content (VWC) measurements during satellite overpass time. The NDVI, CWSI, SI, and SM variables had the highest R² with VWC data (0.71––0.92) on all six dates. This approach has significant implications for improving irrigation management practices, reducing water waste, and increasing crop yields, which can contribute to global food security. The study highlights the potential of RS technology and fuzzy decision-making systems in promoting sustainable agriculture.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"136 ","pages":"Article 104338"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142901787","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}

{"title":"Quantifying heat-related risks from urban heat island effects: A global urban expansion perspective","authors":"Ming Hao ,&nbsp;Xue Liu ,&nbsp;Xia Li","doi":"10.1016/j.jag.2024.104344","DOIUrl":"10.1016/j.jag.2024.104344","url":null,"abstract":"<div><div>Quantifying the urban heat island (UHI) effect and its impact on summer heat-related risk is important for both urban environment and human well-being. Existing studies frequently adopt the static (fixed) urban boundary to define urban/rural area in UHI measurement, overlooking the exacerbation of the urbanization-induced warming during long-term urban expansion and the consequent increase in urban heat risks. Here we measured the global surface UHI (SUHI) intensity up to 7,554 urban patches during 2000–2015 using every five-year dynamic urban boundary, followed by a two-stage analysis based on a Distributed Lag Non-linear Model (DLNM) to quantify the additional heat-related risks caused by the urbanization-induced warming. Our results show that the global average SUHI intensity increased by approximately 10 % in 15 years with distinct seasonal and diurnal variations. The global urban expansion from 2000 to 2015 resulted in an average increase of 0.61℃ (95 % CI = 0.56℃-0.66℃) in summer UHI intensity for newly built-up areas. This urbanization-induced warming further leads to a 20 % (95 % CI = 14.8 %-25.2 %) increase in summer heat relative risk (RR) on average, which implied an average increase of 20 % (95 % CI = 14.8 %-25.2 %) in annual heat-related mortality for the newly built-up areas. Furthermore, over 2.3 % of the world population would experience an RR increase greater than 10 %. This study highlights the importance of dynamic urban boundary for long-time span UHI measurements, providing a deeper understanding of the role of urbanization-induced warming on urban heat risk.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"136 ","pages":"Article 104344"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142901923","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}

{"title":"Satellite images reveal rapid development of global water-based photovoltaic over the past 20 years","authors":"He Ren ,&nbsp;Zhen Yang ,&nbsp;Fashuai Li ,&nbsp;Maoxin Zhang ,&nbsp;Yuwei Chen ,&nbsp;Tingting He","doi":"10.1016/j.jag.2025.104354","DOIUrl":"10.1016/j.jag.2025.104354","url":null,"abstract":"<div><div>Water-based photovoltaics (WPV) have emerged as a promising solution to land-use conflicts associated with solar photovoltaic systems. Accurate monitoring of the spatiotemporal distribution of WPV is essential for evaluating its development potential, environmental impacts, and informing policy decisions. Satellite remote sensing data offer a feasible approach for WPV mapping and monitoring. However, conventional image classification and deep learning methods often limited by sample size requirements, computational costs, and technical complexity, which hinder their widespread applicability. To address these challenges, this study proposes a novel index, the normalized difference photovoltaic index (NDPI), for WPV detection. We generated a global WPV map for the year 2023 using Sentinel-2 MSI imagery and NDPI. Additionally, by integrating NDPI with Landsat time series data, we determined the installation dates of WPV systems and evaluated their development trends from 2000 to 2023. Our results show that: (i) The NDPI demonstrated excellent performance in WPV detection, with overall accuracy for spatial location and installation dates of WPV was 0.935 and 0.927, respectively, and Kappa coefficients of 0.870 and 0.921. (ii) Global WPV coverage in 2023 reached 589.17 km², with Asia being the primary contributor, accounting for over 97 %. China emerged as the leading country, with a WPV area of 472.92 km², significantly exceeding other nations (&lt; 50 km²). (iii) WPV experienced significant growth from 2000 to 2023, particularly after 2015. The increase in WPV area (434.57 km²) from 2015 to 2023 was nearly three times the total area covered in the previous 15 years. The proposed NDPI provides a universal approach for global WPV spatiotemporal monitoring and the update of basic information. It also provides potential for assessing the environmental impacts of WPV across its operational lifecycle.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"136 ","pages":"Article 104354"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142975205","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}

{"title":"Predicting turbidity dynamics in small reservoirs in central Kenya using remote sensing and machine learning","authors":"Stefanie Steinbach ,&nbsp;Anna Bartels ,&nbsp;Andreas Rienow ,&nbsp;Bartholomew Thiong’o Kuria ,&nbsp;Sander Jaap Zwart ,&nbsp;Andrew Nelson","doi":"10.1016/j.jag.2025.104390","DOIUrl":"10.1016/j.jag.2025.104390","url":null,"abstract":"<div><div>Small reservoirs are increasingly common across Africa. They provide decentralised access to water and support farmer-led irrigation, in addition to contributing towards mitigating the impacts of climate change. Water quality monitoring is essential to ensure the safe use of water and to understand the impact of the environment and land use on water quality. However, water quality in small reservoirs is often not monitored continuously, with the interlinkages between weather, land, and water remaining unknown. Turbidity is a prime indicator of water quality that can be assessed with remote sensing techniques. Here we modelled turbidity in 34 small reservoirs in central Kenya with Sentinel-2 data from 2017 to 2023 and predicted turbidity outcomes using primary and secondary Earth observation data, and machine learning. We found distinct monthly turbidity patterns. Random forest and gradient boosting models showed that annual turbidity outcomes depend on meteorological variables, topography, and land cover (R² = 0.46 and 0.43 respectively), while longer-term turbidity was influenced more strongly by land management and land cover (R² = 0.88 and 0.72 respectively). Our results suggest that short- and longer-term turbidity prediction can inform reservoir siting and management. However, inter-annual variability prediction could benefit from more knowledge of additional factors that may not be fully captured in commonly available geospatial data. This study contributes to the relatively small body of remote sensing-based research on water quality in small reservoirs and supports improved small-scale water management.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"136 ","pages":"Article 104390"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143211648","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}

{"title":"RSIT: A waveform retracking method based on reconstructed sea surface height and iterative threshold for coastal altimetry data","authors":"Zejie Tu ,&nbsp;Chuanyin Zhang ,&nbsp;Tao Jiang ,&nbsp;Fuxi Zhao ,&nbsp;Heng Wang ,&nbsp;Fanlin Yang","doi":"10.1016/j.jag.2024.104346","DOIUrl":"10.1016/j.jag.2024.104346","url":null,"abstract":"<div><div>Extending satellite radar altimetry measurements from the open ocean to the coastal zone can improve the accuracy and quality of monitoring coastal sea level. However, radar altimetry waveforms can be distorted by any inhomogeneity in the properties of the surface observed within the footprints, possibly leading to range measurement errors. To address these issues, a coastal retracking method based on reconstructed sea surface height and iterative threshold (RSIT) is proposed in this paper. RSIT involves several steps: First, the sea surface height components are reconstructed as prior information to compute the initial retracking gate. Next, iterate the amplitude scale factor of the entire waveform to identify possible sub-waveforms. After each iteration, continuity between neighboring sub-waveforms is assessed. Eventually, the optimal retracking gate is determined from all identified sub-waveforms. We validated RSIT using Jason-2 data in the coastal regions of Australia and Pakistan. Experimental results show that RSIT can retrieve more available altimetry data and enhance the accuracy by nearly 37.5% and 23.1% compared to ALES within the last few kilometers to the coast, respectively. Moreover, the impact of varied errors in reconstructed sea surface height on RSIT was discussed, with the results reveal that RSIT has strong robustness to errors within 1 m, making it suitable for application in most coastal zones.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"136 ","pages":"Article 104346"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142901788","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}

{"title":"Multimodal urban areas of interest generation via remote sensing imagery and geographical prior","authors":"Chuanji Shi ,&nbsp;Yingying Zhang ,&nbsp;Jiaotuan Wang ,&nbsp;Xin Guo ,&nbsp;Qiqi Zhu","doi":"10.1016/j.jag.2024.104326","DOIUrl":"10.1016/j.jag.2024.104326","url":null,"abstract":"<div><div>Urban area-of-interest (AOI) refers to an integrated urban functional zone with defined polygonal boundaries. The rapid development of urban commerce has led to increasing demands for highly accurate and timely AOI data. However, existing research primarily focuses on coarse-grained functional zones for urban planning or regional economic analysis, and often neglects AOI’s expiration in the real world. They fail to fulfill the precision requirements of Mobile Internet Online-to-Offline (O2O) businesses. These businesses require AOI boundary accuracy down to a specific community, school, or hospital. In this paper, we propose a fully end-to-end multimodal AOI TRansformer (AOITR) model designed for simultaneously detecting accurate AOI boundaries and validating AOI’s reliability by leveraging remote sensing imagery coupled with geographical prior. Unlike conventional AOI generation methods, such as the Road-cut method that segments road networks at various levels, our approach diverges from semantic segmentation algorithms that depend on pixel-level classification. Instead, our AOITR begins by selecting a point-of-interest (POI) of specific category, which can be easily obtained via web crawler, and uses it to retrieve corresponding remote sensing imagery and geographical prior such as entrance POIs and road nodes. This information helps to build a multimodal detection model based on transformer encoder-decoder architecture to regress the accurate AOI polygon. Additionally, we utilize the dynamic features from human mobility, nearby POIs, and logistics addresses for AOI reliability evaluation via a cascaded network module. The experimental results reveal that our algorithm achieves a significant improvement on Intersection over Union (IoU) metric, surpassing previous methods by a large margin. Furthermore, the AOIs produced by AOITR have substantially enriched our AOI library and have been successfully applied on over 10 different O2O scenarios including Alipay’s face scan payment service.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"136 ","pages":"Article 104326"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142929792","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}

{"title":"Assessing differences in work intensity resilience to pandemic outbreaks using large-scale mobile phone data","authors":"Xiaorui Yan ,&nbsp;Tao Pei ,&nbsp;Xi Gong ,&nbsp;Zhuoting Fu ,&nbsp;Yaxi Liu","doi":"10.1016/j.jag.2024.104343","DOIUrl":"10.1016/j.jag.2024.104343","url":null,"abstract":"<div><div>Pandemic outbreaks significantly disrupt human work activity, which is a crucial aspect of urban daily life, potentially causing reduced income or unemployment. These disruptions often vary across different population groups and regions. However, most existing studies focus on general human mobility patterns with limited attention specific to work activity, and conduct separate analyses on population groups and regions, overlooking intra-population differences across regions and inter-population variations within the same region. To this end, we first introduce the concept of work intensity to quantify the work activity. Using large-scale mobile phone data, we then estimate an individual’s work intensity, and characterize the changes in work intensity based on the concept of resilience, i.e., the ability to withstand and recover from a disaster. Finally, we propose a novel analytical framework that integrates both population groups and regions to assess differences in resilience. Herein, we take the pandemic outbreak in Beijing after the sudden relaxation of dynamic zero-COVID policy as a case study due to less policy intervention. Results reveal that females and younger people exhibit lower work intensity resilience, respectively. We also find significant regional differences and several negative features for resilience: short distance to city center, long home-to-work distance, high density of high-paying jobs, low road density, and high density of subway stations. By integrating both population group and region perspectives, we identify vulnerable population groups in specific regions. This integrated perspective can help design more targeted response and recovery strategies, and thereby promote health-related urban resilience and sustainability.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"136 ","pages":"Article 104343"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142975199","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}

{"title":"Diffuse attenuation coefficient and bathymetry retrieval in shallow water environments by integrating satellite laser altimetry with optical remote sensing","authors":"Changda Liu ,&nbsp;Huan Xie ,&nbsp;Qi Xu ,&nbsp;Jie Li ,&nbsp;Yuan Sun ,&nbsp;Min Ji ,&nbsp;Xiaohua Tong","doi":"10.1016/j.jag.2024.104318","DOIUrl":"10.1016/j.jag.2024.104318","url":null,"abstract":"&lt;div&gt;&lt;div&gt;Shallow water environmental information is crucial for the study of marine ecosystems and human activities. There have been numerous satellite remote sensing studies focused on this area. However, accurate information acquisition from remote sensing data remains difficult in this region due to the complexity of the environment and the coupling between benthic reflectance and water column scattering. In this study, we developed a method to retrieve the diffuse attenuation coefficient (&lt;span&gt;&lt;math&gt;&lt;mrow&gt;&lt;msub&gt;&lt;mi&gt;K&lt;/mi&gt;&lt;mi&gt;d&lt;/mi&gt;&lt;/msub&gt;&lt;/mrow&gt;&lt;/math&gt;&lt;/span&gt;), seafloor classification, and bathymetric maps by combining satellite laser altimetry and optical remote sensing imagery in shallow water areas. Firstly, the relationships between remote sensing reflectance (&lt;span&gt;&lt;math&gt;&lt;mrow&gt;&lt;msub&gt;&lt;mi&gt;R&lt;/mi&gt;&lt;mrow&gt;&lt;mi&gt;r&lt;/mi&gt;&lt;mi&gt;s&lt;/mi&gt;&lt;/mrow&gt;&lt;/msub&gt;&lt;/mrow&gt;&lt;/math&gt;&lt;/span&gt;), water depth, and &lt;span&gt;&lt;math&gt;&lt;mrow&gt;&lt;msub&gt;&lt;mi&gt;K&lt;/mi&gt;&lt;mi&gt;d&lt;/mi&gt;&lt;/msub&gt;&lt;/mrow&gt;&lt;/math&gt;&lt;/span&gt; were established based on radiative transfer theory. This method allows for the retrieval of &lt;span&gt;&lt;math&gt;&lt;mrow&gt;&lt;msub&gt;&lt;mi&gt;K&lt;/mi&gt;&lt;mi&gt;d&lt;/mi&gt;&lt;/msub&gt;&lt;/mrow&gt;&lt;/math&gt;&lt;/span&gt; in shallow water regions, overcoming the limitations present in previous studies. Secondly, we eliminated the water column attenuation and obtained the bottom reflectance index (BRI). The BRI allowed us to determine the bottom reflectance and classify the seafloor using the Gaussian mixture model clustering method. This approach can effectively reduce the error in bathymetric inversion caused by variations in bottom reflectance. Finally, we developed a neural network model for bathymetric inversion. The model inputs consist of &lt;span&gt;&lt;math&gt;&lt;mrow&gt;&lt;msub&gt;&lt;mi&gt;R&lt;/mi&gt;&lt;mrow&gt;&lt;mi&gt;r&lt;/mi&gt;&lt;mi&gt;s&lt;/mi&gt;&lt;/mrow&gt;&lt;/msub&gt;&lt;/mrow&gt;&lt;/math&gt;&lt;/span&gt; data and spectral shape data containing physical constraint information, aiming to achieve a robust estimation performance. We conducted the study in two experimental areas (the Bimini Islands and the Yongle Atoll) and compared the results with validation data to evaluate the algorithm performance. The results indicated an agreement between the estimated &lt;span&gt;&lt;math&gt;&lt;mrow&gt;&lt;msub&gt;&lt;mi&gt;K&lt;/mi&gt;&lt;mi&gt;d&lt;/mi&gt;&lt;/msub&gt;&lt;/mrow&gt;&lt;/math&gt;&lt;/span&gt; and the validation data (inferred &lt;span&gt;&lt;math&gt;&lt;mrow&gt;&lt;msub&gt;&lt;mrow&gt;&lt;mi&gt;K&lt;/mi&gt;&lt;/mrow&gt;&lt;mrow&gt;&lt;mi&gt;d&lt;/mi&gt;&lt;/mrow&gt;&lt;/msub&gt;&lt;mn&gt;490&lt;/mn&gt;&lt;/mrow&gt;&lt;/math&gt;&lt;/span&gt; values of 0.062&lt;!--&gt; &lt;!--&gt;m&lt;sup&gt;−1&lt;/sup&gt; and 0.058&lt;!--&gt; &lt;!--&gt;m&lt;sup&gt;−1&lt;/sup&gt;, compared to a validation data range of 0.055–0.087&lt;!--&gt; &lt;!--&gt;m&lt;sup&gt;−1&lt;/sup&gt; and 0.059–0.070&lt;!--&gt; &lt;!--&gt;m&lt;sup&gt;−1&lt;/sup&gt;, respectively). In addition, the seafloor classification accuracy was 86.74 % for the Yongle Atoll area. Finally, the neural network model accurately predicted the bathymetry in the two regions. The accuracy of the bathymetric maps improved significantly with seafloor classification, as indicated by reductions in root mean square error (RMSE) of 0.12 m and 0.15 m, and in mean absolute percentage error (MAPE) by 2.24 % and 5.87 %, respectively. Overall, the propos","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"136 ","pages":"Article 104318"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142825347","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}