Remote Sensing of Environment最新文献

{"title":"A sliding window-based coastal bathymetric method for ICESat-2 photon-counting LiDAR data with variable photon density","authors":"Jinchen He ,&nbsp;Shuhang Zhang ,&nbsp;Wei Feng ,&nbsp;Xiaodong Cui ,&nbsp;Min Zhong","doi":"10.1016/j.rse.2025.114614","DOIUrl":"10.1016/j.rse.2025.114614","url":null,"abstract":"<div><div>Coastal bathymetry is of great significance to the development and protection of islands and reefs. Traditional ship-based sonar bathymetry and airborne LiDAR (Light Detection and Ranging) bathymetry make it difficult to efficiently map the water depth of remote islands and reefs. Notably, the photon-counting LiDAR on board ICESat-2 (Ice, Cloud, and Land Elevation Satellite-2) has the capability of shallow water bathymetry. However, the photon data acquired by this instrument is contaminated with substantial noise of varying density. In this study, a sliding window-based coastal bathymetric method (SWCBM-Ph) is proposed for photon data with variable density. Experiments are carried out on six island coasts as an example, and the results show that the method is effective in extracting underwater terrain photons for bathymetry, with RMSE (Root Mean Square Error) of 0.60 m and 0.53 m on low- and high-density photon datasets separately within water depth of 30 m. Compared with existing bathymetry methods, the SWCBM-Ph is less affected by noise signals, and adapts to variations in photon density, including diversities between different datasets and within the same dataset. Therefore, the proposed method helps to improve the stability of spaceborne photon bathymetry for complex situations in coastal waters.</div></div>","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"318 ","pages":"Article 114614"},"PeriodicalIF":11.1,"publicationDate":"2025-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143031326","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessment of instantaneous sampling on quantifying satellite-derived surface urban heat islands: Biases and driving factors","authors":"Zihan Liu ,&nbsp;Wenfeng Zhan ,&nbsp;Yanlan Wu ,&nbsp;Jiufeng Li ,&nbsp;Huilin Du ,&nbsp;Long Li ,&nbsp;Shasha Wang ,&nbsp;Chunli Wang","doi":"10.1016/j.rse.2025.114608","DOIUrl":"10.1016/j.rse.2025.114608","url":null,"abstract":"<div><div>Land surface temperature (LST) acquired from polar orbiters serves as a critical dataset for investigating daily clear-sky climatology of surface urban heat islands (SUHIs). However, these orbiters only capture instantaneous LSTs at specific overpass times within a diurnal cycle, thus limiting the analysis of temporally sensitive SUHI metrics such as daily mean, maximum, and minimum SUHI intensity (SUHII). Consequently, the representativeness of daily clear-sky SUHI climatology derived from these instantaneous LSTs remains unclear, especially across global cities. Here we employ Aqua &amp; Terra MODIS LST data alongside a well-established diurnal temperature cycle (DTC) model to assess such representativeness of daily clear-sky SUHI climatology, primarily based on the SUHII biases estimated from DTC-derived diurnally continuous and satellite-based temporally discrete LSTs across global cities. This approach discloses the fidelity of satellite-derived instantaneous LSTs to in representing daily clear-sky SUHI climatology. We further dissect the drivers of SUHII biases using the LightGBM model and SHAP algorithm. Our results reveal substantial underestimation of daily mean and maximum SUHIIs alongside overestimation of minimum SUHII when compared to the estimates directly based on instantaneous LSTs. The annual global mean SUHII biases for daily mean, maximum, and minimum conditions are 0.21 ± 0.13 K, 0.51 ± 0.18 K, and − 0.43 ± 0.17 K, respectively. We observe substantial seasonal and geographic variability in SUHII biases, with greater SUHII biases during winter, in snow climates, and across Europe and Oceania when compared to other seasons, climates, and continents. Notably, background climate is the principal contributor (34 %) to variation in SUHII bias, followed by surface properties (28 %), urban metrics (20 %), and human activity (18 %). Our findings emphasize the importance and show the feasibility of correcting SUHII biases in daily clear-sky SUHI climatology derived from instantaneous LSTs from polar orbiters across global cities.</div></div>","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"318 ","pages":"Article 114608"},"PeriodicalIF":11.1,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143020957","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring grazing angle GNSS-R for precision altimetry: A comparative study","authors":"Raquel N. Buendía,&nbsp;Sajad Tabibi,&nbsp;Olivier Francis","doi":"10.1016/j.rse.2025.114604","DOIUrl":"10.1016/j.rse.2025.114604","url":null,"abstract":"<div><div>Sea Level Anomaly (SLA) measurements are essential for understanding oceanic dynamics, climate variability, and climate change impacts. While satellite-based radar altimetry missions are the primary source of such measurements, their spatiotemporal resolution may sometimes be insufficient. This study explores the potential of Global Navigation Satellite Systems-Reflectometry (GNSS-R) as an additional approach for SLA retrieval. It exploits L-Band coherent carrier phase measurements collected by radio occultation receivers in Low Earth Orbit (LEO), known as Grazing angle GNSS-R (GG-R). We compare these GNSS-R measurements with those from traditional radar altimetry, in- cluding Sentinel-3 A/3B, Saral, and Cryosat-2. Our analysis of SLA data spanning from May 2019 to October 2021 reveals an average Root Mean Square Error (RMSE) of ∼47 cm among nearly 10,000 samples. We find that measure- ments derived from both techniques often complement each other when they meet recommended quality standards. Enhancing GG-R estimates could serve as a valuable complement to existing radar altimetry missions, which alone may not provide sufficient data. Furthermore, a comparison exclusively focused on GG-R events has been made to ensure consistency in the Spire GG-R retrievals, resulting in a 25 cm RMSE. Additionally, we conducted an assess- ment to evaluate the coherency and coverage of GG-R measurements. Approximately 24 % of the tracks are coherent, primarily located in the polar regions and calm waters.</div></div>","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"318 ","pages":"Article 114604"},"PeriodicalIF":11.1,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143020959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A robust framework for accurate land surface temperature retrieval: Integrating split-window into knowledge-guided machine learning approach","authors":"Yuanliang Cheng ,&nbsp;Hua Wu ,&nbsp;Zhao-Liang Li ,&nbsp;Frank-M. Göttsche ,&nbsp;Xingxing Zhang ,&nbsp;Xiujuan Li ,&nbsp;Huanyu Zhang ,&nbsp;Yitao Li","doi":"10.1016/j.rse.2025.114609","DOIUrl":"10.1016/j.rse.2025.114609","url":null,"abstract":"&lt;div&gt;&lt;div&gt;Land surface temperature (LST) is a crucial parameter of the surface-atmosphere system, driving the water and heat exchange between the surface and the atmosphere. However, existing LST retrieval methods are highly sensitive to input errors. This study proposed a robust framework for retrieving LST, termed SW-NN, which integrates the physics-based Split-Window (SW) algorithm with a data-driven Neural Network (NN). The framework comprises of two main components: (1) a NN model that estimates SW coefficients as functions of key parameters such as brightness temperature (BT), water vapor content (WVC), land surface emissivity (LSE), and viewing zenith angle (VZA); and (2) a SW model that applies these coefficients to compute LST based on physical principles. By embedding the SW algorithm into the NN's loss function, this integrated design ensures that physical relationships guide the training process. The training data for the framework were generated by simulating satellite BT under a broad range of atmospheric and surface conditions using a radiative transfer model. To address the challenge of input errors, the proposed framework incorporates Gaussian noise into the training data to simulate realistic uncertainties in BT, WVC, and LSE. Specifically, noise with standard deviations of 0.05 K, 10 % of the WVC value, and 0.01 was added to BT, WVC, and LSE, respectively. Simulation analysis on an independent test set demonstrates that the proposed framework achieves a theoretical root-mean-square error (RMSE) of 0.60 K under the noise strategy, outperforming standalone NN and SW models. Sensitivity analysis, conducted using the same noise strategy applied during training, indicates that input errors affect LST retrieval by approximately 0.20 K, significantly enhancing the model's generalization and robustness. The proposed framework was also applied to MODIS data to retrieve LST, which was directly validated against global measurements from fifteen sites. Additionally, the proposed framework was compared with the NN method, the generalized split-window (GSW) method (MOD11 LST), and the Temperature Emissivity Separation (TES) method (MOD21 LST). The results showed that the proposed framework achieved an RMSE of 1.99 K, outperforming the NN method (RMSE = 2.08 K) and the GSW method (RMSE = 2.52 K), and performing comparably to the TES method (RMSE = 2.03 K). Further analysis in arid areas, where LSE accuracy is relatively lower, showed that the proposed framework improved the RMSE to 1.94 K compared to MOD11 LST, which had an RMSE of 3.02 K, utilizing the same LSE inputs. The proposed framework leverages the SW model's mechanism and the NN model's nonlinear fitting capability. It also demonstrates high robustness against input error, particularly LSE error. In summary, the proposed framework achieves robust and accurate LST retrieval, offering interpretability and a significant improvement over existing methods designed for sensors with two the","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"318 ","pages":"Article 114609"},"PeriodicalIF":11.1,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142991982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Measuring river slope using spaceborne GNSS reflectometry: Methodology and first performance assessment","authors":"Yang Wang ,&nbsp;Y. Jade Morton ,&nbsp;J. Toby Minear ,&nbsp;Alexa Putnam ,&nbsp;Alex Conrad ,&nbsp;Penina Axelrad ,&nbsp;R. Steven Nerem ,&nbsp;April Warnock ,&nbsp;Christopher Ruf ,&nbsp;Daniel Medeiros Moreira ,&nbsp;Matthieu Talpe","doi":"10.1016/j.rse.2025.114597","DOIUrl":"10.1016/j.rse.2025.114597","url":null,"abstract":"<div><div>River slope, a crucial parameter in hydrological modeling, has historically been difficult to measure continuously on a regional or global scale. Satellite altimetry missions often have long revisit times, such as 10 to 20 days for the Surface Water and Ocean Topography (SWOT) mission. In this paper, a novel approach is presented utilizing spaceborne GNSS Reflectometry (GNSS-R) to measure river slopes with high accuracy and potentially short revisit times. Our Earth is enveloped in radio signals from over 100 GNSS satellites. These signals can be coherently reflected from river surfaces and detected by low Earth orbit (LEO) satellites with sufficient energy to estimate carrier phase. The carrier phase measurement captures water surface height variations, which can be extracted through modeling of the reflection signal propagation geometry and space environment effects to estimate river slopes. This study processes both the raw intermediate frequency (IF) data obtained by NASA’s Cyclone GNSS (CYGNSS) microsatellites and the grazing-angle GNSS-R data generated by Spire Global nanosatellites to demonstrate the feasibility and performance of the GNSS-R based river slope retrieval. This paper focuses on selected river sections with width greater than <span><math><mo>∼</mo></math></span>500 meters. Detailed methodologies and error analyses are presented, indicating total uncertainty of approximately 0.38 cm/km plus ionospheric TEC model error for CYGNSS and 0.69 cm/km for Spire (with dual-frequency ionospheric correction) over an ideal 5-km river section at 30° elevation angle. The retrieval results are validated in areas with nearby flat water surfaces (such as lakes or wide and slow river sections) and against in situ gauge measurements and satellite altimetry, consistently demonstrating the high accuracy and reliability of spaceborne GNSS-R for measuring river slopes.</div></div>","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"318 ","pages":"Article 114597"},"PeriodicalIF":11.1,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142991981","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrating near-infrared, thermal infrared, and microwave satellite observations to retrieve high-resolution precipitable water vapor","authors":"Zheng Du ,&nbsp;Bao Zhang ,&nbsp;Yibin Yao ,&nbsp;Qingzhi Zhao ,&nbsp;Liang Zhang","doi":"10.1016/j.rse.2025.114611","DOIUrl":"10.1016/j.rse.2025.114611","url":null,"abstract":"<div><div>Various techniques have been developed to monitor water vapor because of its important role in weather forecasting and climate change studies. However, high-resolution, spatially continuous water vapor data remain scarce due to the sparsity of ground stations, coarse observational resolution, unavailability of remote sensing data during cloudy conditions, and systematic biases among different techniques. In this study we developed the Global Navigation Satellite System (GNSS) aided algorithms to retrieve Precipitable Water Vapor (PWV) from near-infrared (NIR), thermal infrared (TIR), and microwave (MW) observations from the Medium Resolution Spectral Imager II (MERSI-II) and the Microwave Radiation Imager (MWRI) onboard the Fengyun-3D satellite. We also proposed an improved iterative tropospheric decomposition algorithm to fuse the multiband PWV data, yielding the NIR + TIR PWV (0.01°), the MW PWV (0.25°), and the fused PWV (0.001°) for Australia. Validation against the GNSS PWV shows that the NIR + TIR PWV has a Root Mean Square Error (RMSE) of 1.45 mm and a bias of 0.07 mm, implying a 34 % improvement over the operational NIR products in terms of RMSE. The MW PWV shows RMSE and bias of 1.86 mm and 0.05 mm. The fused PWV integrates the advantages of different datasets, further enhancing the accuracy by 15 % for the NIR + TIR PWV and 21 % for the MW PWV. This study made the first attempt to retrieve PWV from three-band observations and delivers high-quality PWV products, which fills the data gap for high-resolution, spatially continuous PWV information.</div></div>","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"318 ","pages":"Article 114611"},"PeriodicalIF":11.1,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142991980","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Combining Landsat 5 TM and UAV images to estimate river discharge with limited ground-based flow velocity and water level observations","authors":"Maomao Li ,&nbsp;Changsen Zhao ,&nbsp;Qi Huang ,&nbsp;Tianli Pan ,&nbsp;Hervé Yesou ,&nbsp;Françoise Nerry ,&nbsp;Zhao-Liang Li","doi":"10.1016/j.rse.2025.114610","DOIUrl":"10.1016/j.rse.2025.114610","url":null,"abstract":"<div><div>River discharge plays an indispensable role in maintaining the stability of the hydrosphere system and eco-environment. Previous methods that utilize satellite imagery to estimate discharge over poorly gauged basins are generally tailored for large rivers and heavily reliant on ground-based measurements. Consequently, uncertainties often escalate when these methods are applied to medium-sized rivers. Based on Landsat 5 Thematic Mapper (TM) and unmanned aerial vehicle (UAV) images, this study proposed a framework for estimating the discharge of large and medium rivers with limited ground observations. It comprises (1) a modified C/M method, which considers the spatial heterogeneity of rivers using single-site observation data, and (2) a newly developed method for estimating river bathymetry with zero discharge measurements (RIBA-zero). Results show that, utilizing the modified <em>C</em>/<em>M</em> method, rivers wider than three times the satellite resolution (i.e., 90 m) exhibit a relative root mean square error (rRMSE) of 0.23 in the velocity estimation. Narrower rivers display a slight increase in the rRMSE (0.41), which is still within an encouraging range. For both types of river widths, the accuracy of flow velocity estimation is higher during high-flow periods compared with the low-flow counterparts. In terms of the flow area estimation, the RIBA-zero method is much more suited for parabola-shaped cross-sections (rRMSE = 0.22) and flood seasons (rRMSE = 0.35). Additionally, when replacing 30-m Landsat 5 TM with 10 m-resolution Sentinel-2 imageries, the approaches make a significant improvement in velocity estimation for rivers narrower than 90 m across all periods, exhibiting great potential to estimate discharge in medium rivers with finer resolution satellite imageries. The framework requires a few ground observations for discharge estimates with the Nash–Sutcliffe efficiency coefficient (NSE) reaching ∼0.9, thereby greatly facilitating hydrology-related studies with profound implications for sustainable water resources management worldwide.</div></div>","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"318 ","pages":"Article 114610"},"PeriodicalIF":11.1,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142991983","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CLANN: Cloud amount neural network for estimating 3D cloud from geostationary satellite imager","authors":"Han Lin ,&nbsp;Jun Li ,&nbsp;Min Min ,&nbsp;Feng Zhang ,&nbsp;Keyue Wang ,&nbsp;Qunyong Wu","doi":"10.1016/j.rse.2025.114600","DOIUrl":"10.1016/j.rse.2025.114600","url":null,"abstract":"<div><div>Accurate information on cloud amount vertical structure is crucial for weather monitoring and understanding climate systems. Active sensors from satellites can provide three-dimensional (3D) cloud structure but with limited geographical coverage, passive sensors from satellites have expanded observation coverage but with limited capability on profiling the clouds. Combing active and passive observations from satellites, together with atmospheric reanalysis data, this study proposes a machine learning approach (CLANN, CLoud Amount Neural Network) to construct three-dimensional (3D) cloud amounts at passive observational coverage. Independent validation is conducted for cloud amount estimates derived from combined data of the Advanced Geostationary Radiation Imager (AGRI) onboard Fengyun-4 A and ERA5 using CALIPSO/CALIOP product as reference. The results indicate notable correlations (Pearson's <em>r</em> = 0.73). The cloud-amount-weighted height showed a high consistency in terms of height positioning between CLANN estimations and CALIOP data, with an RMSE of 1.88 km and a Pearson's r of 0.92. Key features such as water vapor band brightness temperature and upper-layer temperature significantly enhanced model accuracy, as revealed by permutation importance analysis. Sensitivity tests highlighted the critical role of the 1.375 μm band in cirrus altitude detection, justifying the model's reliance on daytime observations. Additionally, the 3D statistical results from CLANN in 2019 reveal the seasonal variation details of cloud distribution, further demonstrating its application value in climate analysis.</div></div>","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"318 ","pages":"Article 114600"},"PeriodicalIF":11.1,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142989062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Towards a point cloud understanding framework for forest scene semantic segmentation across forest types and sensor platforms","authors":"Hao Lu ,&nbsp;Bowen Li ,&nbsp;Gang Yang ,&nbsp;Guangpeng Fan ,&nbsp;Han Wang ,&nbsp;Yong Pang ,&nbsp;Zuyuan Wang ,&nbsp;Yining Lian ,&nbsp;Haifeng Xu ,&nbsp;Huan Huang","doi":"10.1016/j.rse.2024.114591","DOIUrl":"10.1016/j.rse.2024.114591","url":null,"abstract":"<div><div>Foliage, wood (i.e., trunk, branch), ground, and lower objects (i.e., grass, shrubs), are key semantic components of forests that play different roles in the forest ecosystem. For understanding forest ecosystem structure and function, Light Detection And Ranging (LiDAR) point cloud is a valuable form of remote sensing observation. The understanding intensively relies on precisely performing semantic segmentation task to segment semantic components from forest point cloud data. However, the semantic segmentation of massive point cloud data from forest scenes remains a significant challenge. The forest environment is highly heterogeneous and complex due to tree species and terrain conditions. Different climate zones lead to varying canopy characteristics and the diversity of LiDAR platforms delivers inconsistent point cloud properties. Heuristic approaches and conventional machine learning approaches inevitably suffer from poor generalization. Additionally, most deep learning methods lack a dedicated network design to address the characteristics of forests. This paper introduces Sen-net, a point cloud understanding network specifically constructed for semantic component segmentation of forest scene point cloud. Sen-net implements three modules tailored for forest characteristics. First, a spatial context enhancement module (SCEM) is designed for providing both global and dataset-level perspectives to mine geometric information and robust features hidden in heterogeneous forest. Second, a semantic-driven detail enrichment module (SDEM) is incorporated to preserve rich geometric details and semantic information thereby enhancing the learning of complex structures in the forests. Finally, an adaptive guidance flow (AGF) is added to seamlessly fuse the semantic and detailed features. Comprehensive experiments were conducted on both self-built Lin3D dataset and public datasets. Sen-net achieved an OA of 97.6 % and 85.1 % MIoU on the Lin3D dataset, and an OA of 94.5 % and 78.2 % MIoU on the public dataset FOR-instance. Results show that Sen-net outperformed the representative forest scene point cloud semantic segmentation approaches and state-of-the-art deep learning networks, and it has the potential to generalize to point cloud data collected by LiDAR from other platforms. It is concluded that Sen-net is a powerful and robust framework with substantial potential for being widely and deeply explored in forest ecosystem studies.</div></div>","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"318 ","pages":"Article 114591"},"PeriodicalIF":11.1,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142981852","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A multi-layer perceptron approach for SIF retrieval in the O2-A absorption band from hyperspectral imagery of the HyPlant airborne sensor system","authors":"Jim Buffat ,&nbsp;Miguel Pato ,&nbsp;Kevin Alonso ,&nbsp;Stefan Auer ,&nbsp;Emiliano Carmona ,&nbsp;Stefan Maier ,&nbsp;Rupert Müller ,&nbsp;Patrick Rademske ,&nbsp;Bastian Siegmann ,&nbsp;Uwe Rascher ,&nbsp;Hanno Scharr","doi":"10.1016/j.rse.2024.114596","DOIUrl":"10.1016/j.rse.2024.114596","url":null,"abstract":"<div><div>Accurate estimation of solar-induced fluorescence (SIF) from passively sensed hyperspectral remote sensing data has been identified as fundamental in assessing the photosynthetic activity of plants for various scientific and ecological applications at different spatial scales. Different techniques to derive SIF have been developed over the last decades. In view of ESA’s upcoming Earth Explorer satellite mission FLEX aiming to provide high-quality global imagery for SIF retrieval an increased interest is placed in physical approaches. We present a novel method to retrieve SIF in the O<span><math><msub><mrow></mrow><mrow><mn>2</mn></mrow></msub></math></span>-A absorption band of hyperspectral imagery acquired by the HyPlant sensor system. It aims at a tight integration of physical radiative transfer principles and self-supervised neural network training. To this end, a set of spatial and spectral constraints and a specific loss formulation are adopted. In a validation study we find good agreement between our approach and established retrieval methods as well as with in-situ top-of-canopy SIF measurements. In two application studies, we additionally find evidence that the estimated SIF (i) satisfies a first-order model of diurnal SIF variation and (ii) locally adapts the estimated optical depth in topographically variable terrain.</div></div>","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"318 ","pages":"Article 114596"},"PeriodicalIF":11.1,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142986893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}