Remote Sensing Applications-Society and Environment最新文献

{"title":"Urban morphology and the heat island effect in African cities: Evidence from Ghana, Togo, and Tanzania","authors":"Stephan Schmidt ,&nbsp;Yucheng Zhang ,&nbsp;Wenzheng Li ,&nbsp;Houpu Li","doi":"10.1016/j.rsase.2026.102005","DOIUrl":"10.1016/j.rsase.2026.102005","url":null,"abstract":"<div><div>Urban heat islands (UHI) are an increasingly urgent concern in rapidly urbanizing regions, yet empirical evidence from Sub-Saharan Africa remains limited. This pilot study examines how urban morphology influences UHI intensity across 388 urban settlements in Ghana, Togo, and Tanzania, adapting conventional approaches to data-poor environments. We integrate MODIS land surface temperature with high-resolution land cover and Africapolis settlement boundaries, introducing an adaptive rural baseline that accounts for elevation and cropland exclusions to isolate urban–rural thermal contrasts. Using class-based and landscape-level metrics, we evaluate the role of land use composition, fragmentation, and settlement form in shaping daytime UHI through ordinary least squares regressions. Similar to studies elsewhere, we show that contiguous urban development intensifies UHI, while fragmented urban fabrics help mitigate heat. However, distinctive patterns also emerge. Peri-urban agricultural cohesion significantly reduces UHI, and irregular settlement shapes, often reflecting ribbon-like development along roads, are associated with stronger UHI effects. These findings diverge from results elsewhere, underscoring the importance of context-specific analysis. Methodologically, the study demonstrates that UHI metrics can be adapted to African cities. The results highlight how preserving peri-urban agriculture and maintaining heterogeneous settlement structures can help reduce heat stress in resource-constrained urban environments.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"42 ","pages":"Article 102005"},"PeriodicalIF":4.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147657812","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":"Seasonal coupling of vegetation, moisture, and thermal regimes in selected irrigated commands of India using landsat time-series","authors":"Dibyendu Dutta","doi":"10.1016/j.rsase.2026.102052","DOIUrl":"10.1016/j.rsase.2026.102052","url":null,"abstract":"<div><div>Irrigation commands are complex agro-hydrological systems in which vegetation vigour, surface moisture, and thermal conditions interact under seasonal climatic forcing and water-management practices. Although satellite-derived indicators such as vegetation indices, land surface temperature, and moisture proxies are widely used to assess irrigation performance, their coupled seasonal behaviour at the irrigation-command scale remains insufficiently explored. This study investigates seasonal eco-hydrological dynamics through an integrated analysis of the Enhanced Vegetation Index (EVI), Normalized Difference Moisture Index (NDMI), and land surface temperature (LST) derived from multi-year Landsat-8 observations, supported by subsurface soil moisture from ERA5-Land and contextually interpreted using SMAP observations.</div><div>Seasonal analysis reveals pronounced contrasts across irrigation commands, with peak vegetation vigour and moisture availability during the post-monsoon season and widespread thermal and moisture stress during the pre-monsoon period. NDMI exhibits the strongest seasonal variability, whereas LST shows comparatively lower variability, indicating dominant regional climatic control. To capture coupled system behaviour, three-dimensional EVI–NDMI–LST feature-space patterns were analysed and systematically reduced into four canonical eco-hydrological regimes representing distinct modes of vegetation–moisture–thermal interaction. These regimes exhibit clear seasonal evolution, with regulated states dominating winter and pre-monsoon periods, weakened coupling and heightened variability during the monsoon, and heterogeneous recovery trajectories during the post-monsoon season.</div><div>Principal component–based geometric characterization and Gaussian Mixture Model (GMM) clustering provide objective confirmation of the identified regimes, with concordance analysis indicating moderate agreement (Adjusted Rand Index, ARI ≈ 0.54–0.55) between clustering-based and visually derived classifications. ERA5-Land soil moisture shows strong seasonal modulation but limited interannual variability, indicating that subsurface moisture acts as a boundary condition rather than a direct determinant of surface regime type.</div><div>These results indicate that irrigation-command behaviour is governed primarily by the efficiency of seasonal coupling among vegetation, moisture, and thermal processes, controlled by both climatic forcing and irrigation management. The proposed regime-based framework provides a physically interpretable and quantitatively robust approach for diagnosing irrigation performance and supporting adaptive management under increasing climatic variability.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"42 ","pages":"Article 102052"},"PeriodicalIF":4.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147858908","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":"Spectral contrast polarity inversion as a transfer failure mechanism in deep learning sand dune segmentation: A cross-desert evaluation using Sentinel-1 and Sentinel-2","authors":"Nawfel El Bouchti ,&nbsp;Nadya Wahid ,&nbsp;Khalid Benhssaine ,&nbsp;Jamal Aabdousse","doi":"10.1016/j.rsase.2026.102060","DOIUrl":"10.1016/j.rsase.2026.102060","url":null,"abstract":"<div><div>Deep learning segmentation models achieve strong source-domain performance for sand dune mapping, yet their transferability across mineralogically distinct desert environments remains insufficiently characterized. This study evaluates four U-Net architectures — Optical, SAR, Early Fusion, and Attention Fusion — trained on Sentinel-1 and Sentinel-2 imagery from a Moroccan source domain under zero-shot transfer, unsupervised domain adaptation, and few-shot fine-tuning across three target environments: Morocco East, Oman, and Lyndon River West, Australia. Under zero-shot transfer, optical-informed architectures collapsed to near-zero IoU at mineralogically inverted sites (Morocco East: 0.000–0.110; Australia: 0.003–0.029), whilst the SAR U-Net achieved the sole above-baseline result at Morocco East (IoU = 0.625; +36.0%). Scalar distributional distance did not predict transfer degradation (r = −0.168, p &gt; 0.05), whereas the sign of the normalized Sentinel-2 B12 mean was associated with all transfer failure outcomes. Unsupervised polarity inversion recovered optical model performance to the class ratio boundary without labelled data. Five-shot fine-tuning elevated optical-informed architectures above source-domain performance at Morocco East (mean IoU = 0.627–0.729 at N = 5), whilst no architecture exceeded the class ratio at Australia at any shot count, confirming a persistent performance ceiling driven by compound spectral and morphological domain shift. The proposed B12 polarity diagnostic correctly identifies transfer failure risk at a normalized mean threshold of −1.5, providing a zero-label pre-deployment screening tool. Monte Carlo Dropout entropy–error correlations inverted from positive at Oman to negative at Australia; few-shot fine-tuning partially restored calibration at Australia (Spearman ρ = +0.145 to +0.319 at N = 20).</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"42 ","pages":"Article 102060"},"PeriodicalIF":4.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147995735","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":"Satellite-derived light exposure and ocular health: Bibliometric mapping of research trends and knowledge structure","authors":"Xuan Zhang ,&nbsp;Yahan Yang ,&nbsp;Danqi Zeng ,&nbsp;Yang Liu ,&nbsp;Haotian Lin ,&nbsp;Qingling Zhang","doi":"10.1016/j.rsase.2026.102053","DOIUrl":"10.1016/j.rsase.2026.102053","url":null,"abstract":"<div><div>As a highly photosensitive organ, ocular health is closely associated with environmental illumination conditions. Optical remote sensing, with its macroscopic monitoring capabilities, provides a complementary approach for characterizing spatiotemporal patterns of light exposure that are difficult to capture using traditional medical methods. To map the development of this cross-disciplinary domain encompassing optical remote sensing, light environment, and ocular diseases, we conducted a bibliometric analysis of publications indexed in the Web of Science Core Collection (WoSCC) from 1995 to 2024, examining temporal evolution, global collaboration, thematic structures, and emerging research fronts. The results revealed an overall increasing trend in annual publications, with the first cross-disciplinary convergence occurring in 2018. International collaboration is generally associated with higher citation impact and more efficient knowledge dissemination, although disparities in research productivity and network connectivity persist across regions, reflecting structural asymmetries in global knowledge production. Research hotspots centered on ultraviolet (UV) radiation and light pollution, with artificial light at night (ALAN) emerging as a rapidly expanding frontier topic. Optical remote sensing technology has undergone significant advancement and continues to evolve toward higher temporal resolution and broader analytical capability. Nevertheless, challenges remain in spectral detection, data integration, and cross-disciplinary coordination. We call for strengthened cross-disciplinary research to build a bridge between light environment, ocular diseases, and optical remote sensing, which can enhance scientific understanding of environmental determinants of ocular health and support evidence-informed environmental management.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"42 ","pages":"Article 102053"},"PeriodicalIF":4.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147956589","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 CNN–RF hybrid approach for deforestation detection using Google Earth Engine satellite imagery","authors":"M.S. Babitha ,&nbsp;Andrushia A. Diana ,&nbsp;N. Anand ,&nbsp;M.Z. Naser","doi":"10.1016/j.rsase.2026.102043","DOIUrl":"10.1016/j.rsase.2026.102043","url":null,"abstract":"<div><div>This paper presents a lightweight and hybrid deep learning strategy that combines Convolutional Neural Networks (CNNs) and Random Forest (RF) classifiers for Land Use and Land Cover (LULC) mapping and detecting changes in the district of Bengaluru, Karnataka, India, between 2018 and 2024. The proposed model utilizes Google Earth Engine (GEE) to operate on multi-spectral Sentinel-2, Sentinel-1 radar backscatter, and topographic features such as elevation and slope. More specifically, the developed deep learning strategy applies the CNN module to efficiently capture the spatial and spectral details, while the RF classifier enhances decision-level accuracy through ensemble learning. Our findings report an accuracy of 98.48% and a Kappa coefficient of 98.10% for the year 2018 and an accuracy of 99.26% and Kappa coefficient of 99.08% for the year 2024, and outperform individual CNN, RF, and traditional ensemble models. Therefore, the proposed model presents a feasible and scalable solution for land use planning and forest monitoring in variable landscapes.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"42 ","pages":"Article 102043"},"PeriodicalIF":4.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147957104","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":"Crop type classification in smallholder agriculture of central and South Asia using Sentinel-1/2 data fusion","authors":"Christoph Raab ,&nbsp;Viet Duc Nguyen ,&nbsp;Brian Barrett ,&nbsp;Aksana Zakirova ,&nbsp;Mehwish Zuberi ,&nbsp;Henryk Alff ,&nbsp;Michael Spies","doi":"10.1016/j.rsase.2026.102007","DOIUrl":"10.1016/j.rsase.2026.102007","url":null,"abstract":"<div><div>Accurate crop monitoring in smallholder-dominated regions is challenging due to fragmented fields, high crop diversity, and often limited ground truth data. This study presents a systematic and transferable framework for crop-type classification in smallholder systems by jointly evaluating multi-sensor data fusion, temporal feature aggregation, feature selection, and model applicability. This study evaluates crop-type classification accuracy across smallholder agricultural landscapes in Central and South Asia (Kazakhstan, Tajikistan, Pakistan), leveraging Sentinel-1 radar and Sentinel-2 optical data separately and combined. Employing Random Forest models, we systematically compare temporal aggregation approaches (monthly, bi-monthly, quarterly) and evaluate the impact of feature selection on model performance. Across all study regions, combined Sentinel-1 and Sentinel-2 data achieved overall classification accuracies of approximately 80–96%, with substantial performance gains relative to single-sensor models, particularly in regions where individual sensors showed limited discrimination capability. Depending on region and sensor, accuracy improvements ranged from a few percentage points to more pronounced gains, reflecting strong benefits of data fusion in heterogeneous smallholder systems. Finer temporal aggregation schemes, including monthly aggregation, yielded additional accuracy gains of approximately 1–3 percentage points compared to coarser aggregations, while feature selection further improved model performance by roughly 2–5 percentage points. Sentinel-1 proved particularly effective for structurally distinct crops such as cotton, while Sentinel-2 substantially improved classification of more diverse crop classes. Application of the Area of Applicability concept enabled spatially explicit identification of well-supported and extrapolated predictions, providing a quantitative basis for uncertainty assessment and future sampling strategies. Together, these results demonstrate the value of an integrated and transferable methodological framework for robust crop-type classification in smallholder agricultural systems using freely available Sentinel data.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"42 ","pages":"Article 102007"},"PeriodicalIF":4.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147710209","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":"Agronomic variables outperform multispectral indices for individual plant yield prediction in Andean quinoa","authors":"Samuel Pizarro ,&nbsp;Erika Garcia ,&nbsp;Esthefany Gavino ,&nbsp;Edilson Requena-Rojas ,&nbsp;Kevin Ortega ,&nbsp;Dennis Ccopi","doi":"10.1016/j.rsase.2026.102027","DOIUrl":"10.1016/j.rsase.2026.102027","url":null,"abstract":"<div><div>Accurate pre-harvest yield estimation is essential for decision-making in high-altitude agriculture. This study evaluated agronomic and multispectral UAV variables for near-harvest prediction of individual quinoa grain weight, with data collected across six phenological stages to identify when predictors achieve reliable performance, under Andean conditions. A total of 374 plants were monitored across six phenological stages at Santa Ana Experimental Station (Huancayo, Peru, 3280 m a.s.l.) during 2024. OLS, Random Forest, Support Vector Machine, and Neural Network models were trained using agronomic-only (AGRO), spectral-only (IND), and combined (COMP) predictor sets, evaluated through 5-fold cross-validation reporting mean ± standard deviation. Agronomic and combined models achieved moderate performance (R² = 0.22–0.25, RPD = 1.10–1.15), suitable for relative plant ranking in breeding programs, while spectral-only models failed across all algorithms (R² ≤ 0.044, CCC ≤0.080), constrained by saturation, phenological decoupling, and canopy heterogeneity. Variable importance analysis confirmed that late-season structural traits dominated predictions, while spectral indices contributed marginally despite including red-edge bands. These results challenge spectral-only approaches for individual plant phenotyping in heterogeneous canopies, demonstrating that integrating simple ground measurements with UAV spectral data is essential for reliable quinoa yield estimation.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"42 ","pages":"Article 102027"},"PeriodicalIF":4.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147710287","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":"Assessment of daytime and nighttime land surface temperature behavior in an arid region: evidence of thermal trends asymmetry","authors":"Lizbeth María Flores-González ,&nbsp;Jesús Gabriel Rangel-Peraza ,&nbsp;Sergio Alberto Monjardin-Armenta ,&nbsp;Wenseslado Plata-Rocha ,&nbsp;Antonio Jesus Sanhouse-García ,&nbsp;Zuriel Dathan Mora-Felix","doi":"10.1016/j.rsase.2026.102021","DOIUrl":"10.1016/j.rsase.2026.102021","url":null,"abstract":"<div><div>In-situ data scarcity has limited the mechanistic understanding of climate trends in arid Northwestern Mexico. This study provides the first systematic quantification and attribution of diurnal Land Surface Temperature (LST) asymmetry in this region from 2000 to 2024. Using a non-parametric analysis of MODIS data coupled with high-resolution national land cover dynamics, the results reveal a severe and well-defined thermal asymmetry: a statistically significant nighttime warming trend (+0.71 °C/decade) contrasted with a net cooling trend during the day (−0.25 °C/decade). This study demonstrates that the most acute manifestations of this nocturnal warming are spatially coupled with anthropogenic land surface modifications, specifically agricultural intensification and urbanization. The loss of nocturnal cooling alters the surface energy balance, acting as a systemic risk multiplier for regional water resources and agricultural viability. These findings establish that analyzing diurnal and nocturnal phases independently, and linking them to land-use dynamics, is essential for identifying climate risks in data-scarce arid ecosystems.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"42 ","pages":"Article 102021"},"PeriodicalIF":4.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147710290","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":"GNSS-IR and spectral remote sensing data fusion for soil moisture estimation","authors":"R. Awad ,&nbsp;F. Kizel ,&nbsp;G. Even-Tzur","doi":"10.1016/j.rsase.2026.101983","DOIUrl":"10.1016/j.rsase.2026.101983","url":null,"abstract":"<div><div>Recent advancements in Global Navigation Satellite System-Interferometric Reflectometry (GNSS-IR) have enabled the extraction of environmental data by analyzing differences between direct and multipath signals. A key application is soil moisture estimation using Signal-to-Noise Ratio (SNR) measurements of reflected signals. However, these methods only provide relative moisture estimates, requiring periodic in-situ measurements to establish the minimum moisture level for each observation period. On the other hand, optical remote sensing estimates soil moisture through pixel reflectance, clearing the need for in-situ measurements but is limited by sensitivity to weather and illumination conditions, cloud cover, ground vegetation cover, and a 3–5-day satellite orbit, hindering continuous estimation. This study further develops the potential of GNSS-IR for soil moisture estimation by introducing a novel, optimized approach to enhance accuracy. We also develop a data fusion model that combines GNSS-IR's continuous, weather-independent measurements with discrete estimates from spectral remote sensing Sentinel-2 imagery. This model enables continuous soil moisture estimation without in-situ measurements. We use datasets from Valencia, Spain, and Kabri, Israel, to evaluate the methodology. Our models achieve an accuracy relative to in-situ data of approximately 0.02 [m³/m³] in soil moisture estimation, outperforming traditional methods, which have an accuracy of around 0.05 [m³/m³].</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"42 ","pages":"Article 101983"},"PeriodicalIF":4.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147613418","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":"Early discrimination of conservation tillage practices in wheat using a novel spectral index from Sentinel-2 time series","authors":"Rajkumar Dhakar ,&nbsp;Vinay Kumar Sehgal ,&nbsp;Parmod Kumar ,&nbsp;Niveta Jain","doi":"10.1016/j.rsase.2026.101967","DOIUrl":"10.1016/j.rsase.2026.101967","url":null,"abstract":"<div><div>Monitoring, Reporting, and Verification (MRV) of regenerative agricultural practices such as conservation tillage is crucial for credible carbon markets and sustainable food systems in India's rice-wheat belt. Addressing this need, we developed a novel, satellite-based approach to discriminate between conventional tillage (CT) and conservation tillage [Happy Seeder (HS) and Super Seeder (SS)] practices of wheat sowing early in the season (during sowing window) using Sentinel-2 MSI time-series data (2020–2022). The analysis was conducted over 146 agricultural fields across multiple districts in Punjab and Haryana, representing heterogeneous smallholder conditions. Spectral analysis showed that SWIR1 (centered at 1613 nm) reflectance is sensitive to a small change in crop residue cover (CRC∼ 8-10%), exhibiting a strong linear relationship with CRC (R² = 0.97, p &lt; 0.01), while NIR/red-edge bands responded primarily to larger CRC changes (CRC &gt;20%). Temporal spectral profiles underscored pronounced distinctions in SWIR1, NIR, and red edge wavelengths corresponding to tillage intensity and CRC levels. Temporal analysis of spectral indices led to the development of a new index, CPSI (Conservation Practice Spectral Index) which integrates the features for sensitivity to non-photosynthetic vegetation, crop residue and tillage practice. Using the temporal maximum CPSI value (CPSI_max) during the sowing window and a single threshold derived from training data, the method achieved an overall classification accuracy of 92% with a Kappa coefficient of 0.81 on independent validation data, effectively distinguishing CT from HS/SS practices. District-wise accuracies ranged from 91% to 98%, demonstrating strong spatial and temporal robustness across years. This research delivers an efficient, scalable, and highly accurate methodology for early detection of conservation tillage, providing a critical tool for robust low-cost MRV in agricultural carbon credit programs and for the promotion of regenerative agricultural practices.</div></div>","PeriodicalId":53227,"journal":{"name":"Remote Sensing Applications-Society and Environment","volume":"42 ","pages":"Article 101967"},"PeriodicalIF":4.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147613421","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}