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

{"title":"Asymmetric adaptation of dryland vegetation to a warming and drying climate over two decades in Xinjiang, China: Evidence from satellite observations","authors":"Haiwei Zhang ,&nbsp;Xuan Zhang ,&nbsp;Fei Zhang ,&nbsp;Jianghua Zheng ,&nbsp;Jinming Yang ,&nbsp;Longhui Li ,&nbsp;Jia Song ,&nbsp;Xu Ma","doi":"10.1016/j.jag.2026.105316","DOIUrl":"10.1016/j.jag.2026.105316","url":null,"abstract":"<div><div>Arid-zone vegetation may adapt to climate warming and increased precipitation by adjusting photosynthetic capacity and modifying its temperature–precipitation response. However, shifts in optimal temperature (T_opt) and precipitation (P_opt) values over recent decades remain poorly quantified. In this study, we provide empirical evidence based on satellite-derived vegetation indices and climatic data, showing that from 2000 to 2020, the arid regions of Xinjiang exhibited significant greening, with over 60% of the area showing stable or improving vegetation activity. During this period, T_opt increased at a rate of 0.028 °C yr⁻¹, while P_opt decreased at 0.034 mm yr⁻¹. The rising T_opt aligns with the trend of increasing air temperatures, whereas the declining P_opt contrasts with rising mean precipitation, highlighting the distinct response to the warming and decrease in precipitation trend in regulating vegetation dynamics in arid environments. These findings suggest that vegetation in arid zones is actively acclimating to warming and decrease in precipitation conditions, potentially mitigating the adverse impacts of climate change on ecosystem productivity more than previously anticipated.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"149 ","pages":"Article 105316"},"PeriodicalIF":8.6,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147798279","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Spatio-temporal variability and canonical seasonal regimes of tropospheric NO2 across India’s non-attainment cities: Insights from TROPOMI, ERA5 meteorology, and trend sensitivity analysis","authors":"Dibyendu Dutta","doi":"10.1016/j.jag.2026.105319","DOIUrl":"10.1016/j.jag.2026.105319","url":null,"abstract":"<div><div>Tropospheric nitrogen dioxide (NO₂) is a critical air pollutant associated with urban emissions, industrial activity, and adverse health outcomes. This study provides a comprehensive, satellite-based assessment of NO₂ variability across 131 non-attainment cities under India’s National Clean Air Programme using TROPOMI observations (2018–2025).</div><div>A pronounced and spatially consistent seasonal cycle is observed, with winter maxima frequently exceeding 30 × 10⁻⁵ mol m⁻² and monsoon minima driven by enhanced wet scavenging and atmospheric mixing. Inter-city variability peaks during winter (∼77–82%) and declines sharply during the monsoon (∼45–51%), highlighting strong seasonal control on spatial heterogeneity. Persistent hotspots align with major urban–industrial corridors, particularly coal-based power and mining regions (e.g., Korba–Anpara), where annual mean concentrations exceed 20 × 10⁻⁵ mol m⁻², while southern and northeastern regions remain comparatively low.</div><div>Meteorological controls are strongly season-dependent, with precipitation showing robust negative correlations (r ≈ −0.47 to − 0.77) and wind-driven dispersion further regulating NO₂ levels, whereas boundary-layer effects are comparatively weak at aggregated scales. Trend analysis reveals predominantly weak and statistically insignificant behaviour, with insignificant transitions dominating (∼46–66%) and ∼ 91–99% of cities remaining stable after excluding COVID-affected years, indicating that short-term perturbations strongly influence apparent trends.</div><div>A key contribution of this study is the identification of five canonical seasonal regimes, demonstrating that diverse urban environments converge into a limited number of physically interpretable temporal patterns. Moderate seasonality dominates (∼67% of cities), while strong seasonal contrasts (∼30%) are concentrated in major industrial regions. Validation with CPCB observations shows moderate agreement (r = 0.41–0.56) with systematic underestimation.</div><div>These findings establish that tropospheric NO₂ variability across India is governed by the interaction of emission intensity, seasonal meteorology, and episodic perturbations, and provide a scalable, regime-based framework for regional air-quality assessment and policy design.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"149 ","pages":"Article 105319"},"PeriodicalIF":8.6,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147798282","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A spatially and temporally transferrable bi-temporal conditional generative adversarial network for landslide extraction","authors":"Bo Yu ,&nbsp;Siyuan Chen ,&nbsp;Fang Chen ,&nbsp;Nurfashareena Muhamad ,&nbsp;Ning Wang ,&nbsp;Lei Wang","doi":"10.1016/j.jag.2026.105317","DOIUrl":"10.1016/j.jag.2026.105317","url":null,"abstract":"<div><div>Accurate landslide extraction from remote sensing imagery is critical for hazard assessment, yet existing methods often struggle to generalize across different times, regions, and sensor modalities. This limitation largely stems from complex terrain, spectral confusion with background surfaces, and severe class imbalance in training data. To address these challenges, we propose BTLE-cGAN, a bi-temporal landslide extraction framework using conditional generative adversarial networks. Unlike prior approaches, BTLE-cGAN directly models the mapping task in an adversarial setting to jointly optimize spatial accuracy and structural realism. The generator integrates a Multi-scale Spectral–Spatial Convolution (MSSConv) module for morphological variation, a Non-Local Context Enhancement (NLCE) module to model long-range dependencies, and a Landslide-Adaptive Convolution (LAC) module that adjusts filters based on predicted shapes to refine boundaries. The discriminator leverages bi-temporal difference features to enforce semantic consistency and topological alignment. To alleviate sample imbalance, we introduce a Potential Landslide Extraction (PLE) strategy that generates contour-guided, land-cover-filtered candidate regions, thereby improving the representativeness and efficiency of both training and inference. Extensive evaluations across regions, time periods, and sensors show BTLE-cGAN consistently outperforms 11 state-of-the-art frameworks, achieving up to 11% average improvement in IoU. It maintains robust performance under temporal shifts, sensor variation, and spatial transfers, offering a scalable, generalizable solution for high-precision landslide monitoring. Our method advances bi-temporal change detection for geohazard mapping and supports future applications in dynamic environments.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"149 ","pages":"Article 105317"},"PeriodicalIF":8.6,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147798277","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Monitoring annual forest carbon stock loss using very high-resolution time series remote sensing images and earth-foundational data","authors":"Zhipan Wang ,&nbsp;Bin Chu ,&nbsp;Zegang Chen ,&nbsp;Yunfei Zhang ,&nbsp;Yatao Li ,&nbsp;Duming Peng ,&nbsp;Sichun Long ,&nbsp;Haibo Zeng","doi":"10.1016/j.jag.2026.105320","DOIUrl":"10.1016/j.jag.2026.105320","url":null,"abstract":"<div><div>Monitoring forest carbon stock loss is crucial for addressing climate change and human sustainability. The forest canopy height (CHM) and change areas are the most important factors for estimating forest carbon stock loss based on multi-modal remote sensing data. Although there are several regional or even global-scale CHM estimation algorithms and change detection methods for long-time series images that have appeared, few researchers consider combining the forest height and long-time series change detection results to estimate the accurate forest carbon stock loss for large-scale regions. To address these challenges, we proposed a new method to evaluate high-precision forest carbon stock loss over large-scale regions based on multi-modal remote sensing data. Firstly, we designed a novel CHM estimation model using Sentinel-1/2, the AlphaEarth embedding data, and Global Ecosystem Dynamics Investigation (GEDI) to acquire annual CHM products. Then, we obtained very high-resolution (VHR) annual forest loss maps based on VHR remote sensing images through an advanced siamese deep learning change detection model, which was trained on a large-scale forest change detection dataset. Finally, combining the annual CHM products and time-series forest change detection results, we can obtain high-precision three-dimensional forest change maps and forest carbon stock loss. We selected the GreenHeart Park (In Hunan Province, China) to evaluate the performance of the proposed method, and we acquired the three-dimensional forest change and carbon stock loss results in this region from 2018 to 2024 with 0.5/1-m VHR remote sensing images. The results indicated that annual carbon stock loss has significantly decreased since 2021. The proposed three-dimensional forest change detection and carbon stock loss estimate framework has a high practical value to be applied in national or even global scales. The open-source code of this manuscript can be seen at <span><span>https://github.com/wzp8023391/ForestCarbonEstimate</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"149 ","pages":"Article 105320"},"PeriodicalIF":8.6,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147850593","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Depth-resolved phytoplankton responses to persistent marine heatwaves in the southern tropical indian ocean","authors":"Qiwei Hu ,&nbsp;Xiaoyan Chen ,&nbsp;Zhanlin Liang ,&nbsp;Yu Huan ,&nbsp;Zili Song","doi":"10.1016/j.jag.2026.105323","DOIUrl":"10.1016/j.jag.2026.105323","url":null,"abstract":"<div><div>Marine heatwaves (MHWs) in the tropical Indian Ocean (TIO) have intensified in duration and frequency during the satellite observing era, causing severe ecological disruptions. However, the vertical structure of MHWs and their effects on phytoplankton across the entire euphotic zone (0–200  m) remain unclear. Here, using BGC-Argo, satellite, and reanalysis data, we analyze a prolonged MHW event (443  days, 2019–2020) in the southern TIO upwelling region, driven by persistent downwelling oceanic planetary waves. Our results show that during austral summer-fall 2019/2020, subsurface-intensified MHWs reduced phytoplankton chlorophyll <em>a</em> concentration (Chla, −20%) and particulate organic carbon (POC, −10%) in the upper mixed layer (0–80  m) via combined thermal stress and nutrient limitation. Below mixed layer (80–150  m), photoacclimation decoupled Chla from biomass, yielding a 30% Chla increase despite of stable POC levels. In austral winter-spring 2019/2020, surface-intensified MHWs suppressed mixed-layer Chla (−40%) more severely than POC (−10%), indicating photoacclimation-mediated carbon retention. This study establishes that subsurface MHWs degrade the deep chlorophyll maximum (DCM) and carbon export, whereas surface-intensified MHWs dominate mixed-layer productivity declines. Moreover, subsurface phytoplankton biomass responses to MHWs may be overlooked by satellites, posing significant threats to mesopelagic biodiversity hotspots.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"149 ","pages":"Article 105323"},"PeriodicalIF":8.6,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147850594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Few-Shot multispectral segmentation of PV expansion and Land-Use dynamics in China","authors":"Xiaopu Zhang ,&nbsp;Huayi Wu ,&nbsp;Shuyang Hou ,&nbsp;Zhangyan Xu ,&nbsp;Yongxian Zhang ,&nbsp;Jianfang Ma ,&nbsp;Dan Liu ,&nbsp;Yuanyi Jiang ,&nbsp;Jianxun Wang","doi":"10.1016/j.jag.2026.105185","DOIUrl":"10.1016/j.jag.2026.105185","url":null,"abstract":"<div><div>Driven by global carbon neutrality initiatives, China’s rapid expansion of photovoltaic (PV) power generation necessitates large-scale and precise extraction of photovoltaic power stations (PPS) for effective resource management. However, in 10 m resolution remote sensing imagery, PPS targets frequently exhibit multi-scale and fragmented spatial distributions. Such characteristics often lead to limited model generalization, high omission rates, and elevated commission errors, particularly under sparse-sample conditions. To address these challenges, this study introduces PPS-SAM, a spectrum- and structure-aware extraction framework developed for sparse-sample scenarios based on the Segment Anything Model (SAM). PPS-SAM integrates a Spectral Enhancement Encoder to fuse near-infrared (NIR) and shortwave-infrared (SWIR) bands, thereby improving the spectral separability of PV targets from heterogeneous backgrounds. It also incorporates a High-Quality Mask Decoder to maintain edge integrity and delineate fragmented arrays more effectively. Evaluated on a newly developed 10 m multispectral PPS dataset (MSPV-Dataset), PPS-SAM demonstrated robust segmentation performance with only 11 training samples (F1: 91.47% ± 0.13%; mIoU: 91.40% ± 0.08%), notably surpassing baseline models trained on the complete 634-sample dataset. Ablation and generalization assessments indicate the effectiveness of each module in enhancing foreground detection and background suppression, with stable performance across diverse, unseen terrains and environmental disturbances (F1: 92.19%; mIoU: 92.19%). Applying this framework, nationwide PPS distribution maps for 2022 and 2024 were generated (excluding distributed rooftop systems). The results indicate that the total PPS area expanded from 3,486.41 km2 to 5,900.89 km2, representing an increase of approximately 70%. Regional analysis shows that Northwest China was characterized by predominantly centralized growth (78.77%), whereas eastern and southwestern regions exhibited significant distributed expansion. Although national spatial clustering weakened slightly (Global Moran’s I decreased from 0.4155 to 0.3112), it intensified within central and southwestern provinces. Land-use transition analysis suggests that new PV installations primarily originated from grasslands (59.04%) and barren lands (96.40%), highlighting substantial land-cover conversion. These spatio-temporal patterns underscore regional disparities in PV expansion and shifting spatial structures. This study offers a robust methodological framework for high-precision PPS identification at 10 m resolution under sparse-sample constraints, supporting efficient renewable energy management and evidence-based policy formulation. The dataset is publicly available via Figshare (<span><span>https://doi.org/10.6084/m9.figshare.29618429)</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"147 ","pages":"Article 105185"},"PeriodicalIF":8.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147278391","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A resource-efficient training framework for remote sensing text–image retrieval","authors":"Weihang Zhang ,&nbsp;Jihao Li ,&nbsp;Shuoke Li ,&nbsp;Ziqing Niu ,&nbsp;Jialiang Chen ,&nbsp;Wenkai Zhang ,&nbsp;Xin Gao ,&nbsp;Xian Sun","doi":"10.1016/j.jag.2026.105174","DOIUrl":"10.1016/j.jag.2026.105174","url":null,"abstract":"<div><div>Remote sensing text–image retrieval (RSTIR) aims to retrieve the matched remote sensing (RS) images from the database according to the descriptive text. Recently, the rapid development of large visual-language pre-training models provides new insights for RSTIR. Nevertheless, as the complexity of models grows in RSTIR, the previous studies suffer from suboptimal resource efficiency during transfer learning. To address this issue, we propose a computation and memory-efficient retrieval (CMER) framework for RSTIR. To reduce the training memory consumption, we propose the Focus-Adapter module, which adopts a side branch structure. Its focus layer suppresses the interference of background pixels for small targets. Simultaneously, to enhance data efficacy, we regard the RS scene category as the metadata and design a concise augmentation technique. The scene label augmentation leverages the prior knowledge from land cover categories and shrinks the search space. We propose the negative sample recycling strategy to make the negative sample pool decoupled from the mini-batch size. It improves the generalization performance without introducing additional encoders. We have conducted quantitative and qualitative experiments on public datasets and expanded the benchmark with some advanced approaches, which demonstrates the competitiveness of the proposed CMER. Compared with the recent advanced methods, the overall retrieval performance of CMER is 2%–5% higher on RSITMD. Moreover, our proposed method reduces memory consumption by 49% and has a 1.4x data throughput during training. The code of the CMER and the dataset will be released at <span><span>[Link]</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"147 ","pages":"Article 105174"},"PeriodicalIF":8.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147278196","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From canopy segmentation to accurate prediction: An UAV-based multi-feature fusion framework for plot-scale ratoon sugarcane seedling counting","authors":"Hongyan Zhu ,&nbsp;Zhihao Dong ,&nbsp;Litao Wei ,&nbsp;Shuai Qin ,&nbsp;Xiaoyan Qin ,&nbsp;Yong He","doi":"10.1016/j.jag.2026.105183","DOIUrl":"10.1016/j.jag.2026.105183","url":null,"abstract":"<div><div>Accurate and efficient monitoring of seedling emergence is critical for early-stage crop management and yield forecasting in sugarcane production. To meet this practical demand for precise field phenotyping, this study developed a high-throughput phenotyping framework leveraging unmanned aerial vehicle (UAV) remote sensing data and machine learning. This framework addresses the critical agricultural challenges of inefficient manual counting and the need for plot-scale monitoring in sugarcane production by enabling high-throughput sugarcane seedling number prediction through the integration of UAV-acquired RGB and multispectral imagery. Specifically, the sugarcane canopy was accurately segmented from the background using K-means clustering, a step that enabled the extraction of canopy area and the generation of a mask for obtaining canopy-level average features (including vegetation indices and texture features). These features together form a comprehensive feature set. Subsequently, six different feature selection methods were used to optimize the feature set, and eight machine learning models were combined for training and evaluation. The results showed that the combination of Gradient Boosting Regression (GBR) and KBest-F feature selection method yielded the optimal prediction performance, with a coefficient of determination (R²) of 0.7641, a root mean square error (RMSE) of 19.42, and a mean absolute error (MAE) of 15.93. Further analysis identified canopy area, the Normalized Difference Red Edge Index (NDRE), red edge contrast, and green entropy as core predictive features. They collectively contribute over 60% of total feature importance, and their synergistic effects support accurate seedling number estimation. This framework offers an efficient, scalable tool for plot-scale seedling monitoring, with substantial potential for precision field management of high-density crops.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"147 ","pages":"Article 105183"},"PeriodicalIF":8.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147278239","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessing the impact of road on sensitivity of large slow-moving landslides to precipitation by integrating multi-temporal InSAR and panel regression","authors":"Yi Zhang ,&nbsp;Wangcai Liu ,&nbsp;Guan Chen ,&nbsp;Tom Dijkstra ,&nbsp;Xingmin Meng ,&nbsp;Xiang Wu ,&nbsp;Jing Chang ,&nbsp;Yuanxi Li ,&nbsp;Yanzhong Yang","doi":"10.1016/j.jag.2026.105192","DOIUrl":"10.1016/j.jag.2026.105192","url":null,"abstract":"<div><div>Human-landscape interactions in mountainous terrains are complex and multi-faceted. Settlements tend to focus on relatively gently undulating terrains, which are often found in areas where ground conditions are weak and thus substantial ground movements prevail. Interventions in these precarious landscapes, such as progressive expansion of interconnecting transport infrastructure, affect the stress balance and hydrology of already critical slopes, potentially enhancing their sensitivity to changes. The mountainous Bailong River Corridor (BRC) in Northwest China is dominated by large slow-moving landslides, where any transport infrastructure expansion has to transit through. A complex interplay of human, precipitation, and seismic factors determines the triggering dynamics of these large movements. This study integrates displacement time series, precipitation, and road distribution to quantify the impact of road emplacement on the sensitivity of large slow-moving landslides to precipitation regionally using panel regression analysis. It is shown that road disturbance significantly amplifies the sensitivity of landslide displacements to precipitation, and paved roads on the large slow-moving landslides increase their sensitivity to precipitation by 40%. Roads (both paved and unpaved) also reduce the threshold of antecedent cumulative precipitation required to trigger significant displacement, shortening the typical period from 132 days to only 120 days. The enhanced response frequency increases large reactivated landslide risk, and impacts road operation and management. This better understanding of the precipitation signature in the dynamics of large slow-moving landslides transited by roads contributes to improving future road planning, enhancing landslide risk mitigation, and strengthening urban resilience in vulnerable alpine environments.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"147 ","pages":"Article 105192"},"PeriodicalIF":8.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147278243","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Discriminating natural and planted forests in subtropical China using Sentinel-2 imagery and inventory data at 10 m resolution","authors":"Haiyang Guo ,&nbsp;Jia Sun ,&nbsp;Zenghui Fan ,&nbsp;Zhen Yu ,&nbsp;Feng Tian ,&nbsp;Xuemei Mao ,&nbsp;Lunche Wang ,&nbsp;Shaoqiang Wang ,&nbsp;Wei Gong ,&nbsp;Feiyue Mao ,&nbsp;Anders Ahlstrom","doi":"10.1016/j.jag.2026.105179","DOIUrl":"10.1016/j.jag.2026.105179","url":null,"abstract":"<div><div>Accurately distinguishing between natural forests and planted forests underpins effective biodiversity monitoring and climate policy, yet their spectral similarity and limited reference data challenge large-scale classification efforts. This study focuses on Guangxi Province, China, combining Sentinel-2 imagery, multi-source ecological indicators—including vegetation traits such as leaf chlorophyll content and LAI—and over 12 million visually interpreted forest stands to map the distribution of natural and planted forests. We assessed pixel- and object-based classification models under various sample scenarios, with accuracy independently validated using additional samples interpreted from high-resolution Google Earth imagery. Model evaluation relied primarily on random splits, supplemented with spatially stratified validation across ecological sub-regions to assess spatial generalization. Results show that the object-based random forest classifier achieved the highest accuracy (OA: 84.52%, F1: 84.04%), with topographic and vegetation functional traits as key predictors. Spatially, natural forests dominate mountainous zones, while planted forests prevail in flatter areas. This work delivers the first 10 m resolution forest type map for Guangxi based on a uniquely large training and validation dataset and demonstrates that combining functional traits with robust sampling improves classification performance. Our framework supports scalable forest monitoring and contributes to improved management and conservation strategies.</div></div>","PeriodicalId":73423,"journal":{"name":"International journal of applied earth observation and geoinformation : ITC journal","volume":"147 ","pages":"Article 105179"},"PeriodicalIF":8.6,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147278245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}