Accurate and timely crop yield prediction is crucial for ensuring food security and maintaining stable agricultural markets, yet leveraging high-temporal-resolution, multi-source data for this purpose presents a big challenge in effectively capturing intricate variable interactions across time, especially during periods of extreme weather events. To address this issue, this study introduces an Attention and Graph Isomorphism Network-enhanced Bidirectional Long Short-Term Memory network (AGB-LSTM), which is specifically designed for estimating countylevel soybean yield in the United States. The proposed model effectively integrated diverse high-temporalresolution time-series data (5-days), including Near-Infrared Reflectance of Vegetation (NIRv), Solar-Included chlorophyll Fluorescence (SIF), and Gross Primary Productivity (GPP), along with environmental covariates. The AGB-LSTM model achieves an accuracy of R2 = 0.67 and rRMSE = 14.46 %, which outperforms traditional and advanced machine learning methods tested, such as Random Forest (RF) (R2 = 0.52, rRMSE = 17.36 %) and Transformer (R2 = 0.60, rRMSE = 15.80 %). Furthermore, sensitivity analysis revealed the capability of the model for accurate and stable yield prediction 1 to 2 months before harvest. Notably, utilizing data with finer temporal resolution (5-day and monthly composite data) continuously improves performance. Specifically, the model performance is R2 = 0.67 and rRMSE = 14.46 % for the 5-day data, and R2 = 0.55 and rRMSE = 16.81 % for the 30-day data. We also highlight the robustness of the model under extreme climate events, maintaining strong performance with R2 = 0.50 and rRMSE = 21.32 %. Finally, the validation against USDA reported yields for major North American soybean regions in 2023 show that AGB-LSTM well captures the spatial patterns of soybean yield. These findings underscore the AGB-LSTM model as a promising and effective method for yield estimation, showcasing large potential for global crop yield forecasting.

As the window for achieving the “30 × 30” target rapidly narrows, identifying areas with high biodiversity value and feasibility for inclusion in conservation networks has become a central challenge in conservation planning. Key Biodiversity Areas (KBAs) are critical to global biodiversity persistence, yet many remain inadequately covered by existing protected areas. It remains unclear which KBAs should be prioritized for inclusion in global conservation networks and what benefits this could deliver. Here we develop a global framework integrating risk assessment, priority identification, and benefit evaluation. We used this framework to assess climate and anthropogenic risk, as well as species extinction risk across mammals, reptiles, amphibians, birds, and plants in terrestrial KBAs, identify priority areas for conservation expansion, and quantify potential benefits. Results showed marked spatial heterogeneity in climate risk, anthropogenic risk, and species extinction risk across KBAs. Climate risk and anthropogenic risk were not significantly correlated, while species extinction risk showed some cross-taxon consistency, especially among mammals and reptiles. Climate risk was positively correlated with extinction risk in some vertebrate, whereas anthropogenic risk showed weak correlations across taxa. Globally, about 49% of KBAs were identified as priority KBAs, with protection coverage of no more than 30%, accounting for 2.08% of terrestrial land area. Incorporating these areas into existing protected areas could increase global conservation coverage to 20.51%, provide coverage for threatened species distribution ranges, especially amphibians, and cover 3.3% of global irrecoverable carbon. These findings provide spatially explicit evidence for expanding conservation toward under-protected KBAs to support the 30 × 30 target.

Accurate soybean yield estimation requires the effective fusion of solar-induced chlorophyll fluorescence (SIF), which is a key indicator of photosynthetic function, and structural information from reflectance-based vegetation indices. However, both SIF and vegetation indices are subject to Sun–sensor geometry, and robust multisource integration that exploits canopy directional signatures remains challenging. To address this issue, we propose M-Net, a physics-guided deep learning framework that explicitly incorporates canopy angular anisotropy for yield prediction. Instead of treating angular effects as noise to be normalized, M-Net incorporates bidirectional reflectance distribution function (BRDF)-derived angular features into an attention-based architecture to encode 3-dimensional canopy angular anisotropy as predictive information. Sensitivity analysis demonstrated that the accuracy of yield estimation decreased as Sun–sensor geometries deviated from the nadir, a trend particularly pronounced for physiological SIF signals susceptible to angular distortion. In comparative experiments, standard recurrent baselines (e.g., gated recurrent unit and long short-term memory) gained little from physics-reconstructed angular anisotropy features. In contrast, M-Net effectively used these anisotropic signatures and converted canopy directional anisotropy into predictive information. Validated across 613 US soybean-growing counties (2019 to 2023), M-Net achieved a high accuracy ( R 2 = 0.69). Notably, yield estimation using coarse-resolution Moderate Resolution Imaging Spectroradiometer data with BRDF-derived multiangular canopy anisotropy features ( R 2 = 0.64) outperformed that of high-resolution Sentinel-2 data with fixed viewing angles ( R 2 = 0.56), suggesting that effectively using angular information may be more important than spatial resolution alone. The results demonstrate that physics-guided deep learning transforms angular anisotropy from uncertainty into a valuable predictive signal, providing a practical approach for multisource crop monitoring.

Soil organic carbon (SOC) is an important component of the global carbon cycle and a vital indicator of ecosystem health, playing key roles in agricultural productivity and climate change mitigation. To trace the spatiotemporal dynamics of SOC in China, a high-resolution (1 km) Soil Organic Carbon Density (SOCD) dataset for the 0–20 and 0–100 cm depths spanning the period from 1985 to 2020 is produced in this study. By integrating Landsat archives, topographic and meteorological data, and 11 743 soil profile measurements, we produced the SOCD dataset from 1985–2020 in China using the Random Forest ensemble learning approach. Specially, a climate zoning strategy was developed to account for the significant environmental heterogeneity across China. The validation of our SOCD estimated results with 0–20 cm depth with independent testing samples showed strong agreement with R2=0.63 and RMSE=2.03 (kg C m−2) for 0–20 cm SOCD estimation and R2=0.62 and RMSE=6.16 (kg C m−2) for 0–100 cm. Moreover, our SOCD estimated results with 0–20 cm depth are aligned well with independent samples (R2=0.76, RMSE=1.75 kg C m−2) and Xu's dataset (R2=0.68, RMSE=1.70 kg C m−2). Furthermore, the validation of our SOCD estimated results with 0–100 cm depth with independent measurements from Dong et al. (2024a) showed strong agreement (R2=0.50, RMSE=4.93 kg C m−2). Furthermore, our SOCD product exhibits high consistency with existing global datasets (HWSD, SoilGrids250 m, and GSOCmap), showing the best fit with SoilGrids250 m (R2=0.74, RMSE=1.03 kg C m−2). Comparisons of model predictions to independent datasets from the 1980s, 2000s, and 2010s in China reveal substantial connections and demonstrate strong performance over time. The estimated SOCD products, along with the compiled raw soil profile observations for both 0–20 and 0–100 cm depths, are openly available via Figshare (https://doi.org/10.6084/m9.figshare.27290310.v2) (Dong et al., 2024b).

Drought, one of the most severe natural disasters globally, has inflicted notable impacts on animal husbandry production, yet the current research on drought impact assessment in pastoral systems is plagued by obvious gaps, such as the lack of comprehensive quantitative evaluations integrating grassland ecosystem and livestock production indicators, unclear quantitative relationships between drought severity gradients and multi-level pastoral impacts, and the absence of validated quantitative assessment frameworks linking drought indices with actual pastoral economic losses. To fill these gaps, this study takes Inner Mongolia grasslands as the research area, analyzes the spatiotemporal characteristics of drought and its impacts on grassland net primary productivity (NPP) over the 50-year period from 1961 to 2012, and quantifies the differential impacts of three representative gradient drought events (1974 moderate, 1986 severe, and 1965 extreme) on grassland NPP, standard hay yield, sheep units and livestock economic losses. The long-term analysis shows that drought frequency in the study area decreases with increasing severity, with the typical steppe having the highest drought frequency and a “nine droughts in ten years” pattern in the central and western regions; drought intensity increases westward, and duration extends with rising severity, and its spatial distribution is highly consistent with the east–west precipitation gradient. Drought is the dominant driver of NPP variation, explaining up to 84% of NPP anomalies, with meadow steppe being the most sensitive to drought and desert steppe showing stronger drought resilience due to adaptive traits such as deeper root systems. The assessment of the three representative drought events reveals that drought impacts exhibit a linear amplification effect with severity, with extreme drought causing an average NPP loss 2.8 times greater, hay yield loss 1.1 times greater, and economic loss 4.4 times greater than those caused by moderate drought, and different grassland types show distinct response characteristics to drought of varying severity. The NPP loss spatial distribution is highly consistent with severe drought areas, and sheep unit loss is directly correlated with drought severity. Most importantly, the study validates a robust quantitative assessment framework (SPI→NPP→hay yield→sheep units→economic loss) with relative errors of less than 9% compared with historical disaster records, which systematically links drought indices with practical pastoral economic losses. This research clarifies the quantitative relationships between drought and multi-dimensional pastoral impacts, and provides actionable scientific insights for drought risk governance in arid and semi-arid pastoral areas such as Inner Mongolia.

Winter wheat is a strategic staple crop underpinning national food security in China, making large-scale and accurate remote sensing mapping essential for arable land management and agricultural regulation. However, in regions such as Jiangsu Province, characterized by highly heterogeneous and fragmented agricultural landscapes, conventional remote sensing classification methods are often limited by inadequate feature representation and weak discriminative capability, resulting in suboptimal mapping accuracy. To address these challenges, this study develops a high-accuracy winter wheat mapping framework that integrates multi-temporal feature fusion and stacked ensemble learning. The Sentinel-2 time-series imagery is employed as the primary data source. Temporal profiles are reconstructed using Savitzky-Golay filtering to suppress noise while preserving phenological dynamics. The multi-dimensional feature set is constructed by combining spectral band reflectance, spectral indices, and texture metrics to capture spatio-temporal crop growth patterns. Then, A stacked ensemble learning architecture is implemented, incorporating four base classifiers: Random Forest (RF), Support Vector Machine (SVM), Classification and Regression Trees (CART), and Gradient Tree Boosting (GTB). Subsequently, the optimized meta-learner is applied to the outputs of these base classifiers to enhance generalization capacity and model robustness. Experimental results demonstrate that the integrated feature fusion strategy significantly improves classification performance compared to single-feature configurations. The optimized stacked model achieves an Overall Accuracy (OA) of 94.74% with a Kappa coefficient of 0.9283, substantially outperforming all individual classifiers. Winter wheat distribution maps for 2021-2023 show strong consistency with statistical yearbook data, with OA of 95.31%, 94.83%, and 94.74%, and Kappa coefficients of 0.9300, 0.9272, and 0.9283, respectively, confirming the temporal stability and transferability of our model. This study establishes a robust and scalable remote sensing identification framework suitable for complex agricultural landscapes, providing methodological support for regional crop monitoring, dynamic cultivated land management, and food security assessment.

Mapping corn distribution is challenging when samples are sparse and optical data is frequently cloudcontaminated. We propose a lightweight sample generation strategy that links peak signals with whole-season consistency to derive high-confidence corn samples. It includes three components: (1) aligning corn peaks within a phenology-aware time window, (2) integrating corn separability with two complementary indices-the corn spectral index, combining red-edge and shortwave infrared signals, and the corn radar index, based on Sentinel-1 polarization channels to ensure structural-dielectric consistency; and (3) enforcing whole-season similarity in timing, shape, and amplitude using a novel Peak- and Temporal-Weighted Dynamic Time Warping (PTW-DTW) algorithm. Compared to existing algorithms, PTW-DTW improves class separability, especially for non-corn crops with similar peaks but different shoulders. Experiments across three sites achieved overall accuracies of 91.40%, 91.70%, and 95.64%, outperforming single-source baselines and remaining stable across years and regions. County-level area estimates correlated well with official statistics (R-2 > 0.98). The generated samples matched well with field data, achieving robust accuracy with fluctuations below 0.5%. Mixed them increased accuracy by about 2%. Relying only on standard composite and common input, this strategy provides consistent regional corn maps and transferable samples in data-limited settings.

Crop type mapping is a core topic in agricultural remote sensing, playing a strategic role in global food security and resource management. Advances in remote sensing and artificial intelligence (AI) have shifted crop type mapping from traditional expert-driven approaches toward data- and knowledge-driven paradigms. However, a systematic synthesis that links key components of crop identification across data sources, methods, and application contexts remains limited. In this review, we analyze the evolution of crop type mapping over the past five decades through a large-scale meta-analysis of more than 19,000 publications retrieved from the Web of Science (WoS) Core Collection. The literature was examined using a large language model-assisted workflow applied to titles, abstracts, keywords, and publication metadata, enabling scalable identification of thematic patterns and methodological trends. Building on this analysis, we organize existing studies within an analytical framework that connects crop sampling strategies, feature engineering, algorithm architectures, and validation practices. The review critically assesses empirical approaches, machine learning (ML) and deep learning (DL) algorithms, transfer learning strategies, and hybrid modeling frameworks, highlighting recent progress in deep feature extraction, learning under limited data conditions, and modeling in complex agricultural environments. Rather than proposing a universal solution, this review provides structured methodological guidance by clarifying the applicability, strengths, and limitations of different approaches under varying environmental conditions, data availability, and mapping objectives.

Fraction of absorbed photosynthetically active radiation (FPAR) is crucial for monitoring vegetation growth and terrestrial carbon cycle. Current physically-based FPAR estimation methods are limited by the high demand for prior field information and computational complexity. Vegetation indices-based empirical methods are simple and widely used, but show limited accuracy and generalizability across diverse vegetation conditions. In this study, we proposed a physically-based method to estimate FPAR using near-infrared albedo of vegetation (NIRv_hemi) calculated from hemispherical reflectance, which requires only near-infrared and red hemispherical reflectances as input. The theoretical derivations based on the spectral invariants theory (p-theory) demonstrate that doubling NIRv_hemi yields a strong 1:1-linear correlation with FPAR. To assess the accuracy of this method, we used ground data of five agricultural sites distributed across Europe, Africa, and South America and simulation datasets from three radiative transfer models (PROSAIL, two-stream approximation, and LESS). Validation against ground measurements across diverse locations yielded an R2 of 0.67 and RMSE of 0.16. Comparisons with the radiative transfer simulations showed that the proposed method has a high accuracy ( R2 ≥0.91, RMSE≤0.06) across varying canopy structures and conditions. Besides, using hemispherical reflectance instead of directional reflectance can comply with the energy conservation law, mitigate directional effects, and improve the accuracy of FPAR estimates. The results highlight that 2·NIRv_hemi could reduce soil impacts and provide robust estimates of FPAR for various biomes except needleleaf forest, and provides a simple but efficient approach for mapping FPAR at a large scale without additional prior knowledge on canopy structure and leaf optical properties.

Abstract. Soil organic carbon (SOC) is an important component of the worldwide carbon cycle as a vital indicator of soil quality and ecosystem health, with significant implications for agricultural production and climate change adaptation and mitigation strategies. Although there are some studies on mapping the spatial distribution of soil organic carbon density (SOCD), the long-time series SOCD products in China are still lacking. Therefore, this study proposed a new algorithm with climatic zoning, aiming to improve the accuracy of predicting SOC densities with depths of 0–20 cm and 0–100 cm from 1985 to 2020. The data sources used in this study include Landsat archives, topographic data, meteorological data, and measured SOCD data. The innovation lies in the zoning models by climate regions using a random forest ensemble learning approach for SOCD estimation in China. The predicted results show that our zoning model outperformed the global model without climate zoning in predicting SOCD with R2=0.55 and RMSE=2.19 for 0–20 cm SOCD estimation and R2=0.52 and RMSE=6.50 for 0–100 cm. Comparably, the SOCD estimation using the global model is with R2=0.46 and RMSE=2.36 for 0–20 cm SOCD estimation and R2=0.44 and RMSE=8.09 for 0–100 cm. Moreover, our 0–20 cm SOCD predictions align well with independent samples (R²=0.69, RMSE=2.01) and are further validated with Xu's dataset (R²=0.63, RMSE=1.82). Furthermore, the comparisons with the published SOC content products including HWSD, SoilGrids250m, and GSOCmap have also shown good consistency, too. Comparably, our predicted SOCD is the best fit with SoilGrids250m products with R2=0.72 and RMSE=1.35. Comparisons of model predictions to independent datasets from the 1980s, 2000s, and 2010s in China reveal substantial connections and a trend of increasing forecast accuracy over time. The predicted SOCD is available via the Figshare (https://doi.org/10.6084/m9.figshare.27290310.v1) (Dong et al., 2024).

The aboveground biomass (AGB) of crops is an essential metric for monitoring crop growth, making timely and accurate AGB forecasting critical for effective agricultural management. The introduction of Unmanned Aerial Vehicles (UAVs) and advanced sensor technologies has revolutionized traditional AGB prediction techniques. Currently, machine learning (ML) combined with UAV data are commonly utilized, along with the Vegetation Index Weighted Canopy Volume Model (CVMVI) for AGB prediction. Nevertheless, there is limited investigation into how these methods perform across different agricultural conditions. This study aims to fill this gap by creating specific methodologies for estimating corn AGB under diverse fertilization and irrigation treatments. We utilized LiDAR, multispectral (MS), thermal infrared (TIR), along with measured AGB and Leaf Area Index (LAI) data from various growth stages to develop a stacking ensemble learning model. This model effectively integrates data from multiple sources, resulting in a strong prediction performance with R2 of 0.86, Mean Absolute Error (MAE) of 1.54 ​t/ha, and Root Mean Square Error (RMSE) of 2.06 ​t/ha. Meanwhile, the analysis of the accuracy of CVMVI revealed its efficacy during the early-stage when corn is short, with its predictive capability diminishing as AGB increases. Consequently, we recommend the CVMVI for early-stage AGB prediction, which can streamline data collection and computational efforts. In contrast, the ML approach, which benefits from data fusion, is more appropriate for predicting AGB during the mid to late growth stages. This study enhances AGB prediction accuracy and speed, providing critical understanding of regional AGB dynamics and supporting better agricultural decision-making.

Accurate and timely crop yield forecasts are critical to realizing global food security, balancing international grain trade, and promoting sustainable agricultural development. By providing consistent and large-scale observations, remote sensing technology has become indispensable in crop yield estimation across local, regional, and global scales. Over the past four decades, numerous crop yield forecasting approaches have been developed, including regression-based statistical models, machine learning, semi-empirical models, crop model-data assimilation (DA), and advanced deep learning (DL) approaches. This review comprehensively explores the latest advancements in these methodologies, critically evaluating their strengths and limitations in practical applications. In particular, this article highlights the challenges associated with spatiotemporal variability, environmental stress factors, and model scalability, offering potential solutions to enhance the accuracy and reliability of regional and global crop yield predictions. Besides, a selection strategy is also outlined, providing guidance on choosing the most appropriate yield estimation methods tailored to specific application objectives, data availability, and geographic scales. We also identify key factors affecting crop yield forecasting and offer insights into future trends and directions of development. Furthermore, we underscore the greatest potential of integrating artificial intelligence (AI) and remote sensing technologies with process-based crop growth models through DA techniques. This fusion holds significant promise for addressing the pressing need for accurate and scalable yield forecasts. As the global demand for food intensifies and the need for sustainable agriculture grows, the development and application of these advanced methodologies will be instrumental in ensuring resilient food systems and supporting sustainable agricultural practices.

Over recent decades, changes in atmospheric ozone and climate have substantially altered surface solar ultraviolet radiation, but the impacts of these changes on crop yields remain unclear. Here we analyze climate data and maize yields from 1992 to 2018 across China to quantify how extreme ultraviolet radiation events-periods of exceptionally high ultraviolet exposure-affect maize production. We show that maize yields decline by about 0.72% for each 1% increase in these events, especially during critical mid-growing stages, although higher soil moisture can reduce this damage. By the 2030 s, extreme ultraviolet radiation could reduce yields by 1.4% and 2.17%, with losses increasing substantially under moderate dry (by 51%) and severe heat stress (by 124%). These findings underscore the necessity of accounting for changes in ultraviolet radiation to improve the accuracy of yield projections.

Forests are critical carbon sinks, and remote sensing has been increasingly used for forest monitoring and biomass estimations. However, species-specific tree-level studies remain limited. In this study, we explored the feasibility of integrating Unmanned Aerial Vehicle (UAV)-Light Detection And Ranging (LiDAR) with highresolution optical satellite imagery to estimate biomass for individual trees across different species. Specifically, we proposed an efficient method that utilizes U-Net networks to extract individual tree crowns from very high-resolution (VHR) optical satellite imagery, and the Dalponte2016 method for segmenting individual tree crowns from UAV-LiDAR point clouds. This approach was then combined with machine learning models-including Random Forest, XGBoost, and four other algorithms-to estimate biomass. The method integrated forest structural parameters derived from LiDAR data with vegetation indices (VIs) obtained from optical imagery to improve tree-level biomass estimations. The proposed method accurately estimated biomass for 53 trees (R2 = 0.89, rRMSE = 34%) using species-specific datasets, showing an average 25.2% increase in R2 and a 14.8% reduction in rRMSE. Species-specific datasets show an 11.6% increase in R2 compared to methods without VIs, and a 22.2% improvement over methods using only VIs. SHapley Additive exPlanations (SHAP) analysis shows that the volume feature played a key role in model performance and remained stable throughout the training process. Overall, the proposed approach enhances individual tree biomass and carbon stock estimations compared to traditional approaches by single-source dataset, showing great potential for large-scale precise forest carbon monitoring using multi-source remote sensing data.

Urban agglomerations, as emerging competitive geographical units in the era of globalization, grapple with the challenge of reconciling rapid urbanization and ecological dynamics, thereby influencing regional sustainability. This predicament is particularly pronounced in dual-core urban agglomerations like Chengdu-Chongqing, necessitating a delicate balance in their interplay. Our study establishes an assessment framework for the synergistic development of ecological environments and urbanization in dual-core urban agglomerations. Leveraging Remote Sensing and Geographic Information System (GIS) techniques, we conduct a multiscale analysis of urbanization and ecological environment synergies. Our findings reveal that: 1) Over the past two decades, the ecological quality of Chengdu-Chongqing urban agglomeration has exhibited a fluctuating yet ascending trend, with nighttime light data indicating continuous and rapid urbanization. 2) The synergistic development of the dual-core urban agglomeration unfolds in distinct stages, influenced by cyclical national policies and unforeseen natural disasters during 2005–2015. Scale differences in the degree of coordinated development within urban agglomeration necessitate strategic differentiation. 3) The trajectory of dual-core urban agglomeration development persists, revealing conspicuous intraregional gaps that, if excessively disparate, could compromise sustainable regional development. This study not only offers scientific decision support for the dual-core urban agglomeration’s development but also advances regional ecological civilization, providing developmental insights for analogous urban agglomerations worldwide.

The accurate simulation of bidirectional reflectance distribution function (BRDF) across varied crop residue cover (CRC) scenarios is pivotal for crop residue monitoring and management. Addressing the limitations of prior research in simulating BRDF for cropland with CRC, we have developed the novel crop residue-covered bidirectional reflectance (CRBR) model. This model couples geometric optical (GO) and radiative transfer (RT) model, which involves adding a clumping index and crop residue tilt angle (CRTA) distribution function through terrestrial laser scanning to parameterize the spatial distribution of covered crop residue. The validation of the CRBR model was conducted using corn residue cover data from Lishu County, Jilin Province, China, collected in April 2023. The results demonstrated strong alignment between the simulated and measured multiangle bands reflectance [ R-2 = 0.90 , root-mean-square error (RMSE) = 0.03, and mean absolute percentage error (MAPE) = 8.91%]. Under various CRC scenarios, the CRBR model consistently outperformed linear mixed models ( R-2 >= 0.99 , RMSE <= 0.02 , MAPE <= 4.14 % versus R-2 >= 0.97 , RMSE <= 0.05 , and MAPE <= 23.69 %). Sensitivity analysis revealed the impact of key model parameters on reflectance simulation. Furthermore, we also examined the adaptability of our model under different moisture conditions and CRC scenarios, confirming its robustness and flexibility. The CRBR model not only helps our understanding of RT in crop residue-soil scenarios but also offers a promising approach for efficient and precise CRC estimation on a regional scale. Such advancements in the CRBR model hold significant implications for conservation tillage monitoring, biomass energy reserve estimation, and cropland carbon storage capacity assessment.

Aiming at the problems of high complexity, false detection and missing detection of maize big spot based on UAV image, an improved algorithm for maize big spot detection was proposed. The algorithm is based on EMA and the improved YOLOv8-BiFPN feature pyramid network. By adding the efficient multi-scale EMA attention mechanism module, the capturing ability of detail information is improved, thus enhancing the feature extraction ability of the model. The YOLOv8 structure is improved into YOLOV8-BIFPN feature pyramid network by integrating BiFPN structure, which can extract context information more efficiently. By introducing WloU loss function, low quality samples in training data are filtered effectively, and the generalization ability of the model is improved. In this paper, the accuracy P was increased by 2.7%, the recall rate R was increased by 4.7%, the average accuracy mAP50 was increased by 3.1%, and the model size was reduced by 2.78M. Compared with other YOLO algorithms, the proposed method has significant advantages in the detection of corn big spot disease.

Sun-induced chlorophyll fluorescence (SIF) is increasingly recognized as a non-destructive probe for tracking terrestrial photosynthesis. Emerging developments in spectral invariants theory provide an innovative and efficient approach for representing SIF radiative transfer processes at the canopy scale. However, modeling leafscale fluorescence based on the spectral invariants properties (SIP) remains underexplored. In this study, the spectral invariants theory is employed for the first time to model the leaf-scale total, backward and forward fluorescence (leaf-SIP SIF). The leaf-SIP SIF model separates the leaf-scale radiative transfer process into two distinct components: the wavelength-dependent one associated with leaf biochemical properties, and the wavelength-independent component linked to leaf structural characteristics. The leaf structure-related effects are characterized by two spectrally invariant parameters: the photon recollision probability (p) and the scattering asymmetry parameter (q), which are parameterized using the directly measurable leaf dry matter. Evaluation against field measurements shows that the proposed leaf-SIP SIF model has a good performance, with coefficient of determination (R2) of 0.89, 0.89, 0.90 and root mean squared errors (RMSE) of 1.28, 0.69, 0.74 Wm- 2 mu m- 1sr- 1, respectively for the total, backward, and forward fluorescence (660-800 nm). The leaf-SIP SIF model with a more concise formulation demonstrates comparable performance with the widely used Fluspect model. The leaf-SIP SIF model provides a simple and efficient approach for simulating leaf-scale fluorescence, with the potential to be integrated into a unified SIP-based model framework for simulating the radiative transfer processes across the soil-leaf-canopy-atmosphere continuum.

Conservation tillage has gained increasing attention as a crucial approach to mitigating cropland degradation, improving oil quality, and ensuring food security. As a primary corn-producing region in China, Jilin Province requires accurate dentification of maize cultivation areas with crop residue cover exceeding 30%, which is vital for remote sensing monitoring and Effective management of conservation tillage zones. This study focuses on Jilin Province and uses Sentinel-1 SAR and Sentinel-2 MSI imagery acquired from May to November 2022 to extract spectral bands, vegetation indices, SAR backscatter features, and Iemporal statistical metrics, thereby constructing a multi-source classification feature dataset. A Random Forest classifier was trained and validated using field-collected samples, with hyperparameter tuning to optimize model performance for conservation illage mapping. The results demonstrate that: (1) In terms of feature dimensionality, the model constructed from multi-source emote sensing imagery demonstrated superior accuracy compared to single-source models. Notably, the M5 model integrating pectral features, vegetation indices, SAR characteristics, and temporal patterns achieved optimal recognition performance with a Kappa coefficient of 93.35% and an Overall Accuracy of 94.56%. Compared to single source approaches, this fused model emonstrated superior performance in both land cover classification and boundary delineation, (2) In terms of temporal dimensionality, the M5-6 model, built using continuous imagery from May to November, outperformed the model relying solely An November imagery, with Kappa and OA increasing by 15.23% and 12.43%, respectively. This approach effectively reduced Interference from other crop types and enhanced the model's temporal adaptability and stability. (3) Spatial optimization using qonnected component labeling further refined classification results, The M5-6-A model effectively removed small noise patches while preserving field boundaries, enhancing spatial consistency and visual quality. Furthermore, comparative analysis with Contemporaneous official statistical data demonstrates that the M5-6-A model achieved a relative error of merely 0. 16. confirming us reliability for practical implementation. The proposed multi-source, time-series classification method demonstrates strong potential for crop residue cover monitoring and supports evidence-based decision-making in sustainable agriculture and cropland Jonservation.