Remote Sensing of Environment最新文献

{"title":"Modeling 3D radiative transfer for maize traits retrieval: A growth stage-dependent study on hyperspectral sensitivity to field geometry, soil moisture, and leaf biochemistry","authors":"Romain Démoulin ,&nbsp;Jean-Philippe Gastellu-Etchegorry ,&nbsp;Sidonie Lefebvre ,&nbsp;Xavier Briottet ,&nbsp;Zhijun Zhen ,&nbsp;Karine Adeline ,&nbsp;Matthieu Marionneau ,&nbsp;Valérie Le Dantec","doi":"10.1016/j.rse.2025.114784","DOIUrl":"10.1016/j.rse.2025.114784","url":null,"abstract":"<div><div>This study integrates a dynamic plant growth model with a three-dimensional (3D) radiative transfer model (RTM) for maize traits retrieval using high spatial–spectral resolution airborne data. The research combines the Discrete Anisotropic Radiative Transfer (DART) model with the Dynamic L-System-based Architectural maize (DLAmaize) growth model to simulate field reflectance. Comparison with the 1D RTM SAIL revealed limitations in representing row structure effects, field slope, and complex light–canopy interactions. Novel Global Sensitivity Analyses (GSA) were carried out using dependence-based methods to overcome limitations of traditional variance-based approaches, enabling better characterization of hyperspectral sensitivity to changes in leaf biochemistry, canopy architecture, and soil moisture. GSA provided complementary results to assess estimation uncertainties of the proposed traits retrieval method across growth stages. A hybrid inversion framework combining DART simulations with an active learning strategy using Kernel Ridge Regression was implemented for traits estimation. The approach was validated using ground data and HyPlant-DUAL airborne hyperspectral images from two field campaigns in 2018 and achieved high retrieval accuracy of key maize traits: leaf area index (LAI, R²=0.91, RMSE=0.42 m²/m²), leaf chlorophyll content (LCC, R²=0.61, RMSE=3.89 <span><math><mi>μ</mi></math></span>g/cm²), leaf nitrogen content (LNC, R²=0.86, RMSE=1.13 × 10⁻² mg/cm²), leaf dry matter content (LMA, R²=0.84, RMSE=0.15 mg/cm²), and leaf water content (LWC, R²=0.78, RMSE=0.88 mg/cm²). The validated models were used to generate two-date 10 m resolution maps, showing good spatial consistency and traits dynamics. The findings demonstrate that integrating 3D RTMs with dynamic growth models is suited for maize trait mapping from hyperspectral data in varying growing conditions.</div></div>","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"327 ","pages":"Article 114784"},"PeriodicalIF":11.1,"publicationDate":"2025-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144130112","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":"Estimating crop biophysical parameters from satellite-based SAR and optical observations using self-supervised learning with geospatial foundation models","authors":"Mahya G.Z. Hashemi ,&nbsp;Hamed Alemohammad ,&nbsp;Ehsan Jalilvand ,&nbsp;Pang-Ning Tan ,&nbsp;Jasmeet Judge ,&nbsp;Michael Cosh ,&nbsp;Narendra N. Das","doi":"10.1016/j.rse.2025.114825","DOIUrl":"10.1016/j.rse.2025.114825","url":null,"abstract":"<div><div>Accurate knowledge of vegetation water content (VWC) and crop height is crucial for agricultural management, environmental monitoring, and for satellite-based retrieval algorithms for geophysical variables. Traditional methods to estimate VWC, primarily rely on optical indices, which has limitations of biomass saturation, and sensitivity to atmospheric conditions. This study introduces a novel application of geospatial foundation models (GFMs), leveraging extensive, unlabeled datasets through self-supervised learning to enhance the skill of VWC and crop height estimation. We developed a comprehensive model integrating Sentinel-1 A C-band SAR and Sentinel-2 A/B indices with weather parameters to estimate soybean and corn VWC and crop height.</div><div>Our research study area spans a variety of climatic zones and management practices, from the humid continental climate of Iowa and Michigan to the subtropical environment of Florida, encompassing both irrigated and non-irrigated fields as well as diverse tillage practices. We compared the performance of Single-Task Learning GFM (STL-GFM), Multi-Task Learning GFM (MTL-GFM), and machine learning techniques including Random Forest (RF), and XGBoost (XGB) to evaluate their effectiveness in estimating VWC and crop height.</div><div>Results demonstrated that STL-GFM outperforms other methods in accuracy and generalizability. For VWC estimation, STL-GFM achieved R² values of 0.90 and 0.89 for soybean and corn, respectively. For crop height, R² values reached 0.95 for soybean and 0.98 for corn. The integration of SAR, optical, and climate data provided more reliable estimations than using individual data sources.</div><div>Feature importance analysis identified NDVI, NDWI, VH backscatter, and precipitation as key drivers for accurate VWC and height estimations. The red-edge band emerged as significant for VWC estimation but showed limited importance for height prediction. Notably, surface roughness demonstrated a noticeable impact on corn VWC and height estimations, while soil moisture exhibited less influence than initially anticipated. Notably, without directly incorporating soil moisture and surface roughness data, but by including diverse field conditions in training and validation, the STL-GFM model demonstrated strong generalization capabilities. This study highlights the potential of GFMs in advancing crop monitoring techniques, offering more reliable data for precision agriculture, and supporting sustainable farming practices across diverse agricultural landscapes.</div></div>","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"327 ","pages":"Article 114825"},"PeriodicalIF":11.1,"publicationDate":"2025-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144130113","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 novel correlation-hypothesis based single channel method for land surface temperature retrieval with reduced atmospheric dependency","authors":"Xiu-Juan Li ,&nbsp;Hua Wu ,&nbsp;Zhao-Liang Li ,&nbsp;José Antonio Sobrino ,&nbsp;Xing-Xing Zhang ,&nbsp;Yuan-Liang Cheng","doi":"10.1016/j.rse.2025.114817","DOIUrl":"10.1016/j.rse.2025.114817","url":null,"abstract":"<div><div>As one of the critical parameters in the land-atmosphere exchange processes, land surface temperature (LST) plays an essential role in various domains, such as climate change, urban heat island effect, disaster monitoring, and evaporation retrieval. Thermal infrared (TIR) remote sensing is one of the main approaches to obtaining LST on a large scale. For the sensors with only one TIR channel, the single-channel (SC) methods are commonly and effectively used to retrieve LST, as they are most suitable under such limitations. However, atmospheric correction is essential for the SC methods, which involves significant uncertainty and complexity. To reduce the atmospheric dependency of SC methods, this study proposes a Correlation-Hypothesis based Single-Channel (CH-SC) method to retrieve LST. In this method, the LST can be retrieved using the top-of-atmosphere (TOA) brightness temperature from a single TIR channel and the LSEs from two virtual adjacent channels, while atmospheric water vapor content (WVC) is used solely to assess atmospheric conditions. Consequently, the CH-SC method exhibits the least sensitive in atmospheric parameter errors compared to existing SC methods. This inherent robustness results in superior stability of retrieval accuracy, enhancing its practicality for real applications. Subsequently, the CH-SC method was applied to Landsat 7 data, alongside the mono-window (MW) method and generalized single-channel (GSC) method. The retrieved LSTs were compared with in-situ measurements for validation. As a result, the CH-SC method exhibited strong performance compared to in-situ measurements, with an RMSE of 2.83 K in SURFRAD sites and 4.02 K in BSRN sites, which was comparable to Landsat 7 LST product (3.15 K at SURFRAD and 4.26 K at BSRN) and outperforming other SC methods. Generally, compared to the existing methods, the proposed method exhibits minimal dependence on atmospheric information while ensuring superior accuracy and stability, even under high water vapor conditions. That holds significant application value, especially for the sensors with limited TIR channels to enable real-time on-orbit computation of LST.</div></div>","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"327 ","pages":"Article 114817"},"PeriodicalIF":11.1,"publicationDate":"2025-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144125264","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":"Canopy BRDF differentiation on LAI based on Monte Carlo Ray Tracing","authors":"Abdelaziz Kallel ,&nbsp;Yingjie Wang ,&nbsp;Johan Hedman ,&nbsp;Jean Philippe Gastellu-Etchegorry","doi":"10.1016/j.rse.2025.114785","DOIUrl":"10.1016/j.rse.2025.114785","url":null,"abstract":"<div><div>Radiative transfer models (RTM) enable the simulation of remote sensing observations and can therefore be useful for sensitivity analyses and model inversions, for example to determine the biophysical properties of vegetation. For this purpose, the calculation of observation derivatives is crucial. In this study, we propose to differentiate vegetation RTM based on Monte Carlo Ray tracing, PolVRT, as a function of the leaf area index (LAI). The variation of LAI is done considering the average leaf area (<span><math><mi>u</mi></math></span>). The difference between simulations corresponding to two areas close to each other (<span><math><mi>u</mi></math></span> and <span><math><msup><mrow><mi>u</mi></mrow><mrow><mo>′</mo></mrow></msup></math></span>) is used to calculate the derivative as the limit when <span><math><msup><mrow><mi>u</mi></mrow><mrow><mo>′</mo></mrow></msup></math></span> approaches <span><math><mi>u</mi></math></span>. We propose in this work to adjust traced paths for <span><math><mi>u</mi></math></span> to simulate (<span><math><msup><mrow><mi>u</mi></mrow><mrow><mo>′</mo></mrow></msup></math></span>), but such paths are weighted to correct their bias. This weighting is based on the technique of Importance Sampling. It increases the weighting of likely paths and conversely decreases it of unlikely ones. We have made a correction for the hot spot effect, since there is a strong dependency between the incident and backscattered paths. Our approach performances are verified using some discrete ROMC scene parameters and compared with the standard finite difference technique.</div></div>","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"327 ","pages":"Article 114785"},"PeriodicalIF":11.1,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144115339","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":"Using sub-diurnal surface-air temperature difference anomaly derived from Himawari-8 geostationary satellite and meteorological grids for early detection of vegetation drought stress: Application to Australia's 2017–2019 Tinderbox Drought","authors":"Dejun Cai ,&nbsp;Tim R. McVicar ,&nbsp;Thomas G. Van Niel ,&nbsp;Randall J. Donohue ,&nbsp;Yuhei Yamamoto ,&nbsp;Stephen B. Stewart ,&nbsp;Kazuhito Ichii ,&nbsp;Matthew P. Stenson","doi":"10.1016/j.rse.2025.114768","DOIUrl":"10.1016/j.rse.2025.114768","url":null,"abstract":"&lt;div&gt;&lt;div&gt;Satellite land surface temperature (&lt;span&gt;&lt;math&gt;&lt;msub&gt;&lt;mi&gt;T&lt;/mi&gt;&lt;mi&gt;s&lt;/mi&gt;&lt;/msub&gt;&lt;/math&gt;&lt;/span&gt;) provides valuable information on vegetation drought stress via its physical linkage to plant stomatal activity and transpiration. New-generation geostationary satellites offer opportunities to monitor sub-diurnal variations in &lt;span&gt;&lt;math&gt;&lt;msub&gt;&lt;mi&gt;T&lt;/mi&gt;&lt;mi&gt;s&lt;/mi&gt;&lt;/msub&gt;&lt;/math&gt;&lt;/span&gt; and thus track plant physiological stress response occurring at sub-daily timescales. Nevertheless, the potential of satellite &lt;span&gt;&lt;math&gt;&lt;msub&gt;&lt;mi&gt;T&lt;/mi&gt;&lt;mi&gt;s&lt;/mi&gt;&lt;/msub&gt;&lt;/math&gt;&lt;/span&gt; and its derived metrics for early detection of vegetation drought stress before visible canopy changes occur has not been widely assessed. Here, we developed a parsimonious Surface-Air Temperature Difference Anomaly (SATDA) method for tracking vegetation drought stress using the cumulative sub-diurnal difference from late-morning to early-afternoon between &lt;span&gt;&lt;math&gt;&lt;msub&gt;&lt;mi&gt;T&lt;/mi&gt;&lt;mi&gt;s&lt;/mi&gt;&lt;/msub&gt;&lt;/math&gt;&lt;/span&gt; from the Himawari-8 geostationary satellite and hourly air temperature (&lt;span&gt;&lt;math&gt;&lt;msub&gt;&lt;mi&gt;T&lt;/mi&gt;&lt;mi&gt;a&lt;/mi&gt;&lt;/msub&gt;&lt;/math&gt;&lt;/span&gt;) from meteorological grids. SATDA utilised &lt;span&gt;&lt;math&gt;&lt;msub&gt;&lt;mi&gt;T&lt;/mi&gt;&lt;mi&gt;s&lt;/mi&gt;&lt;/msub&gt;&lt;mo&gt;−&lt;/mo&gt;&lt;msub&gt;&lt;mi&gt;T&lt;/mi&gt;&lt;mi&gt;a&lt;/mi&gt;&lt;/msub&gt;&lt;/math&gt;&lt;/span&gt; as the physical driving gradient for sensible heat flux (&lt;em&gt;H&lt;/em&gt;) to capture anomalous sensible heating due to reduced plant transpiration. We used SATDA to monitor the spatio-temporal patterns of the 2017–2019 Tinderbox Drought in southeast Australia. We benchmarked the skill of SATDA in forecasting visible drought-induced vegetation greenness decline against both conventional water availability-based indices (i.e., precipitation and soil moisture anomalies) and existing satellite &lt;span&gt;&lt;math&gt;&lt;msub&gt;&lt;mi&gt;T&lt;/mi&gt;&lt;mi&gt;s&lt;/mi&gt;&lt;/msub&gt;&lt;/math&gt;&lt;/span&gt; indices (i.e., Temperature Condition Index and Temperature Rise Index) across diverse climates and land covers. SATDA effectively captured a rapidly intensifying flash drought event at multi-week timescales (Jul to Sep 2019) embedded within the multi-year Tinderbox Drought, which contributed to detrimental impacts on agricultural production and increased wildfire risk. SATDA showed the best vegetation greenness forecast skill in the transitional semi-arid and sub-humid climates, with forecast correlation &gt;0.5 at 32-day lead time. The advantage over water availability-based indices was more evident in woody-dominated ecosystems than herbaceous-dominated ecosystems, likely due to the importance of physiological regulations by trees during droughts such as deeper roots and stronger stomatal control. SATDA, based on &lt;span&gt;&lt;math&gt;&lt;msub&gt;&lt;mi&gt;T&lt;/mi&gt;&lt;mi&gt;s&lt;/mi&gt;&lt;/msub&gt;&lt;mo&gt;−&lt;/mo&gt;&lt;msub&gt;&lt;mi&gt;T&lt;/mi&gt;&lt;mi&gt;a&lt;/mi&gt;&lt;/msub&gt;&lt;/math&gt;&lt;/span&gt;, showed overall better vegetation greenness forecasts than two &lt;span&gt;&lt;math&gt;&lt;msub&gt;&lt;mi&gt;T&lt;/mi&gt;&lt;mi&gt;s&lt;/mi&gt;&lt;/msub&gt;&lt;/math&gt;&lt;/span&gt;-only indices, especially in woody vegetation. Finally, SATDA showed consistently greater advantage over water availabil","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"327 ","pages":"Article 114768"},"PeriodicalIF":11.1,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144105807","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 scalable, annual aboveground biomass product for monitoring carbon impacts of ecosystem restoration projects","authors":"Clement Atzberger ,&nbsp;Markus Immitzer ,&nbsp;Kyle S. Hemes ,&nbsp;Mathias Kästenbauer ,&nbsp;Josué López ,&nbsp;Talita Terra ,&nbsp;Clara Rajadel-Lambistos ,&nbsp;Saulo Franco de Souza ,&nbsp;Kleber Trabaquini ,&nbsp;Nathan Wolff","doi":"10.1016/j.rse.2025.114774","DOIUrl":"10.1016/j.rse.2025.114774","url":null,"abstract":"<div><div>Restoring natural ecosystems has the potential to remove billions of tons of CO₂ annually through the end of the century, but rigorously measuring the climate impacts of restoration activities on the ground remains elusive. Ecosystem restoration interventions across hundreds or thousands of smallholder properties require robust above-ground biomass (AGB) products at high spatial (deca-metric: 10–30 m) resolution for annual monitoring, reporting, and verification (MRV). In addition to ongoing monitoring, historical AGB time series across the region are also necessary. Historical maps are for example needed for eligibility checks and the selection of appropriate counterfactuals, i.e., to establish a dynamic performance benchmark. We present a novel AGB product based on a recently developed foundation model leveraging progress in self-supervised learning (SSL) techniques from multi-spectral Earth Observation (EO) time series. The foundation model is non-contrastive and condenses all available spectral observations acquired within a year into a few, orthogonal and highly informative representations at 10 m (for Sentinel-2) and 30 m (for Landsat 7/8). Combined with spatially sparse Global Ecosystem Dynamics Investigation (GEDI) full-waveform measurements at two relative heights (RH₉₅ and RH₁₀), but otherwise without any further fine-tuning, we are able to estimate forest biomass with an RMSE of &lt;25 Mg/ha, when validated against 38 in-situ AGB measurement sites across a range of agroforestry (cacao and oil palm) and restoration age classes. Compared to five openly available datasets – most of them not available at annual time steps – our approach reduces the RMSE by 15–55%. We demonstrate the scalability of our approach, by producing annual AGB maps covering the entire state of Para, Brazil, for the years 2013 to 2024. The approach is computationally efficient, fully self-supervised without relying on contrastive samples, and can therefore be scaled to global coverage, even under conditions of high cloudiness.</div></div>","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"327 ","pages":"Article 114774"},"PeriodicalIF":11.1,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144105806","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":"Mapping the first dataset of global urban land uses with Sentinel-2 imagery and POI prompt","authors":"Shuping Xiong ,&nbsp;Xiuyuan Zhang ,&nbsp;Haoyu Wang ,&nbsp;Yichen Lei ,&nbsp;Ge Tan ,&nbsp;Shihong Du","doi":"10.1016/j.rse.2025.114824","DOIUrl":"10.1016/j.rse.2025.114824","url":null,"abstract":"<div><div>An up-to-date, detailed global urban land use map is essential for disclosing urban structures and dynamics as well as their differences across different regions. However, generating an accurate global urban land use map remains challenging due to the complex diversity of land use types and the uneven availability of data. Existing methods, which either rely solely on remote sensing imagery or treat supplementary data like point-of-interest (POI) as mandatory inputs, fail to account for regional data disparities and the complex relationships between different data modalities. In this study, we propose an urban land use mapping framework optimized with POI prompts. First, we acquire global urban Sentinel-2 imagery, POI data, and labeled LU samples from Google Earth Engine (GEE) and OpenStreetMap (OSM), and then propose a POI-Prompt Urban Land-use Mapping Network (PPUL-Net), which utilizes POI prompts to enhance classification accuracy and produce reliable predictions in those regions lacking POI data. Consequently, a global land use dataset (GULU) with a 10 m resolution in 2020 has been produced at the first time. Experimental results show that GULU has an overall accuracy of 84.59 %, demonstrating robust performance across continents. Incorporating POI data improved the accuracies for some challenging categories, such as commercial and institutional lands, by 7.32 % and 17.66 %, respectively. Additionally, using POI as prompts instead of direct pixel-level fusion with imagery increased accuracy by 2.92 %. Finally, analysis of the GULU dataset reveals that Europe and North America exhibit high land use diversity, implying mature urban structures, whereas sub-Saharan Africa and South America are predominantly characterized by residential and undeveloped areas. This dataset provides invaluable insights for urban planning, development monitoring, and sustainable development assessments.</div></div>","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"327 ","pages":"Article 114824"},"PeriodicalIF":11.1,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144099323","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 novel adaptive similarity-based ecological niche model for the endangered Yunnan snub-nosed monkey (Rhinopithecus bieti) using UAV LiDAR data","authors":"Guoshuai Hou ,&nbsp;Xin Shen ,&nbsp;Sang Ge ,&nbsp;Yong Zhang ,&nbsp;Lin Cao","doi":"10.1016/j.rse.2025.114804","DOIUrl":"10.1016/j.rse.2025.114804","url":null,"abstract":"<div><div>Ecological niche models (ENMs) are crucial for identifying habitat distribution patterns, understanding habitat preferences, and formulating effective conservation policies. However, accurately quantifying the three-dimensional (3D) structure of habitats, a fundamental component, presents challenges. These estimations heavily depend on the quality of original samples (presence/absence), yet reliable absence data requires prolonged and repeated observations, limiting both efficiency and accuracy. In the study, we focused on the endangered Yunnan snub-nosed monkey (<em>Rhinopithecus bieti</em>), listed on the International Union for Conservation of Nature (IUCN) Red List. We developed an adaptive similarity-based model that introduced a “similarity” pseudo-absence sampling approach for ecological niche modeling using fine-scale (20 m) 3D environmental variables from UAV LiDAR data. This approach integrated geographic similarity with an adaptive kernel density estimation (AKDE) method to prioritize pseudo-absence data sampling and then employed three typical machine learning models (SVM, BRT, and RF) for prediction, verifying the feasibility of this approach and offering direct insights into habitat distribution and preferences. The results indicated that the AKDE method provided the best fit in measuring similarity features. Through the model, the performance of estimations exhibited improved (AUC = 0.89–0.94, TSS = 0.71–0.82, and COR = 0.69–0.79), with average increases of 7 %, 14 %, and 12 %, respectively. The RF model produced more coherent suitable habitats, identifying regions at higher elevations (3100 m–3300 m) with preferences for low understory vegetation density (2–5 m, &lt;10 %), moderate canopy relief ratio (&gt; 0.35), lower tree height (10 m–25 m), and sunny slopes (0.60–1). Our findings demonstrate that integrating UAV LiDAR data with ecological niche modeling, along with the improved pseudo-absence sampling approach, enhances habitat assessment and offers significant potential for advancing conservation strategies.</div></div>","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"326 ","pages":"Article 114804"},"PeriodicalIF":11.1,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144107943","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":"Leveraging transfer learning and leaf spectroscopy for leaf trait prediction with broad spatial, species, and temporal applicability","authors":"Fujiang Ji ,&nbsp;Fa Li ,&nbsp;Hamid Dashti ,&nbsp;Dalei Hao ,&nbsp;Philip A. Townsend ,&nbsp;Ting Zheng ,&nbsp;Hangkai You ,&nbsp;Min Chen","doi":"10.1016/j.rse.2025.114818","DOIUrl":"10.1016/j.rse.2025.114818","url":null,"abstract":"<div><div>Accurate and reliable prediction of leaf traits is crucial for understanding plant adaptations to environmental variation, monitoring terrestrial ecosystems, and enhancing comprehension of functional diversity and ecosystem functioning. Currently, various approaches (e.g., statistical, physical models) have been developed to estimate leaf traits through hyperspectral remote sensing and leaf spectroscopy. However, the absence of high-performing, transferable, and stable models across various domains of space, plant functional types (PFTs) and seasons hinder our ability to quantify and comprehend spatiotemporal variations in leaf traits. This study proposes robust and highly transferable models for better predicting leaf traits with hyperspectral reflectance. Initially, three datasets were assembled, pairing common leaf traits — chlorophyll (Chla+b), carotenoids (Ccar), leaf mass per area (LAM), equivalent water thickness (EWT) — with leaf spectra measurements collected across diverse geographic locations in the U.S. and Europe, PFTs, and seasons. Measurements were acquired using spectroradiometers (e.g., ASD FieldSpec 3/4/Pro and SVC HR-1024i) with integrating spheres, leaf clips, and contact probes. We then developed transfer learning-based hybrid models that incorporated the domain knowledge of radiative transfer models (RTMs) through pretraining processes and were well-constrained by fine-tuning with field measurements. Through comparison with other state-of-the-art statistical models, including partial-least squares regression (PLSR) and Gaussian Process Regression (GPR), as well as pure physical models, we found that the proposed transfer learning models achieved better predictive performance and higher transferability. Specifically, compared to other statistical models and pure RTMs, the transfer learning model exhibited higher coefficient of determination (<em>R</em>^<em>2</em>) values with range of 0.01 to 0.79, lower normalized root mean square error (NRMSE) with range of 0.06 % to 33.25 % in model performance. Additionally, the models exhibited improved transferability, with higher <em>R</em>^<em>2</em> values range from 0.04 to 0.32, lower NRMSE range from 0.08 % to 30.81 %. The findings underscore that transfer learning models through integrating domain knowledge from RTMs and limited observations, can harness the advantages of both RTMs and statistical models and serve as a promising approach for effectively predicting leaf traits.</div></div>","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"326 ","pages":"Article 114818"},"PeriodicalIF":11.1,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144088835","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":"GROUNDED EO: Data-driven Sentinel-2 LAI and FAPAR retrieval using Gaussian processes trained with extensive fiducial reference measurements","authors":"Luke A. Brown ,&nbsp;Richard Fernandes ,&nbsp;Jochem Verrelst ,&nbsp;Harry Morris ,&nbsp;Najib Djamai ,&nbsp;Pablo Reyes-Muñoz ,&nbsp;Dávid D.Kovács ,&nbsp;Courtney Meier","doi":"10.1016/j.rse.2025.114797","DOIUrl":"10.1016/j.rse.2025.114797","url":null,"abstract":"<div><div>Due to their importance in monitoring and modelling Earth's climate, the Global Climate Observing System (GCOS) designates leaf area index (LAI) and the fraction of absorbed photosynthetically active radiation (FAPAR) as essential climate variables (ECVs). The Simplified Level 2 Biophysical Processor (SL2P) has proven particularly popular for decametric (i.e. 10 m to 100 m) retrieval of these ECVs. Comprehensive validation has shown that due to simplifying assumptions in the underlying radiative transfer models (RTMs), biases persist in SL2P retrievals. To avoid RTM assumptions altogether, an empirical data-driven approach might be considered. Yet, such a strategy has historically been prevented by the limited quantity and quality of available in situ reference measurements, as well as the large number of training samples traditionally required by machine learning regression algorithms. New opportunities are now offered by recently established continental-scale environmental monitoring networks, advances in automated data processing and uncertainty evaluation, and machine learning regression algorithms that require many fewer training samples. The Ground Reference Observations Underlying Novel Decametric Vegetation Data Products from Earth Observation (GROUNDED EO) project was initiated to take advantage of these opportunities. We describe the empirical data-driven LAI and FAPAR retrieval approach adopted within the project, involving i) generation of a database containing over 16,000 fiducial reference measurements covering 81 National Ecological Observatory Network (NEON), Integrated Carbon Observation System (ICOS), and Terrestrial Ecosystem Research Network (TERN) sites between 2013 and 2022, ii) development of an empirical data-driven algorithm for Sentinel-2 LAI and FAPAR retrieval based on Gaussian processes, and iii) evaluation of GROUNDED EO retrievals through intercomparison with the current state-of-the-art in decametric retrieval (i.e. SL2P, and a modified version of SL2P developed by the Canada Centre for Remote Sensing – SL2P-CCRS), as well as validation against unseen fiducial reference measurements. In the majority of cases (and despite not making use of ancillary data such as land cover), the empirical data-driven GROUNDED EO retrievals were subject to reduced bias than those from SL2P and SL2P-CCRS, as well as increased fulfilment of user requirements (i.e. 74% of LAI and 69% of FAPAR retrievals overall). Consequently, the approach has potential to reduce uncertainty in key inputs for climate monitoring and modelling, agricultural and forest management, and biodiversity assessment.</div></div>","PeriodicalId":417,"journal":{"name":"Remote Sensing of Environment","volume":"326 ","pages":"Article 114797"},"PeriodicalIF":11.1,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144067364","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}