Leaf area index (LAI) is an important structural parameter of crops and it is usually estimated non-destructively using reflectance spectra from various reflectometers. Prevailing models, often trained on single-crop and singleyear data, lack generalizability. As rotation crops with similar morphology, rice and wheat present an opportunity to develop generalized models; however, their spectral response patterns are not well compared, and adaptable multi-year, multi-crop LAI models remain scarce. To bridge this gap, we developed a generalized LAI estimation model for both crops by integrating physically-based simulation with data-driven deep learning. Key steps included canopy spectral simulation, data augmentation, and model construction with a 1D-CNN and transfer learning. The PROSAIL model was employed to simulate canopy reflectance spectra, with crop growth stages stratified into two phenological phases: sowing-heading stage (LAI: 0.01-5, increment: 0.2) and headinggrouting stage (LAI: 3-8, increment: 0.2). To enhance ecological fidelity, the LSMM was integrated to simulate mixed spectral scenarios involving soil background, water interactions, and spike contributions, while 5% Gaussian noise was systematically introduced to approximate real-world environmental variability. The results showed that the R2 values of the SMOTE-1D-CNN model for the different datasets (four rice and two wheat) ranged from 0.62 to 0.87, and the RMSE values ranged from 0.55 to 1.22. The model achieved a relatively high R2 (0.79 f 0.09) for rice LAI estimation but exhibited a larger RMSE (0.8 f 0.29). For wheat, the R2 was slightly lower (0.74 f 0.17), while the RMSE was smaller and more stable (0.56 f 0.01). These discrepancies reflect how crop characteristics or data distribution may influence estimation accuracy. SMOTE is used as a data enhancement to reduce the "high underestimation" phenomenon of the model, and the model performance is stabilized when the multiplicity of the sample size (n) is greater than or equal to 5. And the model input feature importance is only related to the original sample (the original unenhanced dataset) and does not change with "n". This study demonstrates that a hybrid methodology, fusing physically-based simulation with deep learning, offers significant potential for robust, multi-crop LAI inversion, providing novel insights and technical support for crop monitoring and management.

Precise monitoring of wheat phenology (BBCH scale) is essential for agricultural optimization, yet UAV-based single-phase monitoring encounters spectral ambiguities where multiple vegetation indices correspond to identical growth stages. A dual-mode framework integrating time-series reconstruction with hybrid deep learning was developed to resolve this limitation. UAV multispectral and digital imagery (333 plots, 2023-2024) enabled reconstruction of daily-resolved vegetation indices, color/texture features, and BBCH stages using Gaussian, PCHIP, and linear fitting to mitigate environmental noise. Synthetic datasets incorporating Gaussian noise (5-100 % relative intensity) simulated field variability. Feature selection was optimized through Competitive Adaptive Reweighted Sampling (CARS) and Variance Inflation Factor (VIF). Hybrid CNN-GRU and CNN-LSTM architectures surpassed standalone networks by resolving spectral ambiguities in single-phase data and leveraging temporal patterns during time-series analysis. Time-series models attained maximum accuracy under noise-free conditions (CNN-GRU: R2 = 0.90-0.98, RMSE = 3.61-7.65 BBCH units), with accuracy decreasing proportionally to noise intensity. Conversely, single-phase models demonstrated peak performance at 20 % noise intensity (CNN-GRU: R2 = 0.56-0.70, RMSE = 15.33-17.22 BBCH units), achieving optimal balance between robustness and practicality for real-time farm monitoring. Extreme noise (100 %) distorted feature distributions (7.25-8.73x expansion), validating controlled augmentation. A novel Rate of Phenological Development (RPDW) -quantified as the slope of BBCH progression-was derived to inform breeding programs, while the noiseoptimized single-phase approach enables resource-efficient phenology tracking for family farms. This work bridges methodological innovation (adaptive noise strategies, hybrid architectures) with scalable solutions for precision agriculture, advancing UAV-based phenology monitoring in both academic and applied contexts. (c) 2025 The Authors. Publishing services by Elsevier B.V. on behalf of KeAi Communications Co., Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Understanding the spatial and temporal distribution of irrigated cropland at the field scale is essential for managing irrigation water use and addressing the water-food nexus. While global and regional irrigation products exist, they often classify irrigated crops based on machine learning principles, where irrigated crops outperform rainfed ones. However, these methods typically lack mechanistic representation and are rarely applicable at the field scale over long time series. Additionally, identifying irrigated cropland in dual-season systems poses challenges due to temporal heterogeneity, leading to potential misclassification. To address these issues, we constructed a 3D canopy feature space including hydrothermal characteristics (1-precipitation/ P, 2-actual evapotranspiration/AET) and spectral characteristic (3-NDVI). This approach is based on two mechanisms: the impact of irrigation on water vapor cycling and its role in promoting crop growth. We introduced a novel cross-region Slope Length Index (SLI) to map irrigated and rainfed crops at the field scale. Our method involved downscaling NDVI and AET using spectral fusion techniques (STF) on Google Earth Engine (GEE), followed by fitting a robust rainfed line (AET =-125.41 + 0.84 x P, R2 = 0.70) at the provincial scale, and calculating the SLI. Then A case of irrigation map (Irri_HNP) was generated by a threshold for crop water supply and demand, achieving >= 38 % accuracy improvement on overall accuracy (OA = 0.973) compared to existing products. The SLI method also exhibited strong stability when generalized to the national scope (AET =-74.41 + 0.82 x P, R2 = 0.73), maintaining robustness in both drought and humid years (AET =-177.08 + 0.82 x P, R2 = 0.69). The method's scalability and transferability have been rigorously validated across diverse regions and environments, spanning from provincial to national scales. This validation achieved an OA of 0.922, demonstrating robust performance under heterogeneous conditions. Furthermore, the framework provides actionable insights for field-scale crop management and agricultural water governance.

Soil organic carbon (SOC) plays a crucial role in soil functions, ecosystem health, and carbon cycling. Accurately estimating SOC content is essential for sustainable agricultural production. Traditional spectral methods, particularly visible-near-infrared (VNIR) and mid-infrared (MIR) spectroscopy, are extensively used for SOC estimation. While multi-source data fusion can improve model performance, existing fusion algorithms often struggle to effectively capture multi-band integrated features from multiple sensors. To overcome this limitation and improve the accuracy of SOC estimation, we propose a novel deep learning model, SOCNet, which integrates multi-source VNIR and MIR spectral data through the Spectral-to-Image Transform (SIT) technique. The SIT converts one-dimensional spectral into informative dual-bands images, which are subsequently processed and fused using a multi-channel convolutional neural network (MC-CNN) to enhance the precision of SOC content prediction. To assess SOCNet's performance, we compared it against three CNN models using individual SIT images (SIT-CNNs), three partial least squares regression (PLSR) models (MIR-PLSR, VNIR-PLSR, VNIR-MIRPLSR), and three 1D-CNN models using VNIR and MIR spectral data. Results showed that the SIT technique significantly enhanced the spectral responsiveness to SOC, achieving a maximum absolute Pearson correlation coefficient (|r|) of 0.96. SIT-CNN models outperformed traditional PLSR models, particularly the SIT-CNN model utilizing VNIR spectra alone, where the R2 increased from 0.79 to 0.95 and RMSE decreased from 91.52 to 43.36 g/kg. Furthermore, feature fusion at various levels within the CNN architecture led to further enhancements in SOC prediction accuracy. Among the evaluated configurations, SOCNet's Scheme II achieved the highest prediction accuracy, with an R2 of 0.99, an RMSE of 19.83 g/kg, and a MAE of 12.30 g/kg. Compared to other models, SOCNet reduced RMSE and MAE by at least 36.22 % and 38.84 %, respectively. These findings highlight that SOCNet provides a superior advantage in predicting SOC content, making it promising for applications in precision agriculture.

Remote sensing of leaf area index (LAI) has been a strong interest in recent decades because of its significance in crop growth assessment and modeling. Yet there are wide variations and clear divergences among the chosen bands, spectral indices and model forms in existing studies, even for the same kind of crop. This study aimed to figure out the underlying implications of different spectral ranges used in previous LAI estimations and identify the bands and model form that are most suitable for generic estimation. Integrated datasets of wheat from scenario simulations with a multiple-layer canopy radiative transfer model and field campaigns over various planting conditions were used to account for various interferences on LAI estimation. Saturation was found generally appearing when visible reflectance (typically red, blue and green) was used, while LAI estimation was generally sensitive to leaf angle and observation geometry if visible and/or near-infrared (770-790 nm and 840-880 nm) reflectance was used. The LAI estimation involving red edge was easily affected by chlorophyll, while the estimation with 920 nm and 1080 nm was prone to wheat spike organ. The potential band ranges for generic LAI estimation were spotted as 739-760 nm, 918-925 nm and 1080-1100 nm to avoid saturation, the effect of observation geometry and leaf angle, and three nearby water-sensitive reflection dips. Difference form was found as the promising band combination for generic LAI estimates. A generic estimation model for wheat LAI was then proposed and proved stable and outstanding from low to high LAI under various interferences without saturation. The findings are expected to provide a revealing insight into the generic remote estimation of canopy LAI.

Significance The explosive development of agricultural big data has accelerated agricultural production into a new era of digitalization and intelligentialize. Agricultural big data is the core element to promote agricultural modernization and the foundation of intelligent agriculture. As a new productive forces, big data enhances the comprehensive intelligent management decision-making during the whole process of grain production. But it faces the problems such as the indistinct management mechanism of grain production big data resources, the lack of the full-chain decision-making algorithm system and big data platform for the whole process and full elements of grain production. Progress Grain production big data platform is a comprehensive service platform that uses modern information technologies such as big data, Internet of Things (IoT), remote sensing and cloud computing to provide intelligent decision-making support for the whole process of grain production based on intelligent algorithms for data collection, processing, analysis and monitoring related to grain production. In this paper, the progress and challenges in grain production big data, monitoring and decision-making algorithms are reviewed, as well as big data platforms in China and worldwide. With the development of the IoT and high-resolution multi-modal remote sensing technology, the massive agricultural big data generated by the "Space-Air-Ground" Integrated Agricultural Monitoring System, has laid an important foundation for smart agriculture and promoted the shift of smart agriculture from model-driven to data-driven. However, there are still some issues in field management decision-making, such as the requirements for high spatio-temporal resolution and timeliness of the information are difficult to meet, and the algorithm migration and localization methods based on big data need to be studied. In addition, the agricultural machinery operation and spatio-temporal scheduling algorithm based on remote sensing and IoT monitoring information to determine the appropriate operation time window and operation prescription, needs to be further developed, especially the cross-regional scheduling algorithm of agricultural machinery for summer harvest in China. Aiming to address the issues of non-bi-connected monitoring and decision-making algorithms in grain production, as well as the insufficient integration of agricultural machinery and information perception, a framework for the grain production big data intelligent platform based on digital twins is proposed. The platform leverages multi-source heterogeneous grain production big data and integrates a full-chain suit of standardized algorithms, including data acquisition, information extraction, knowledge map construction, intelligent decision-making, full-chain collaboration of agricultural machinery operations. It covers the typical application scenarios such as irrigation, fertilization, pests and disease management, emergency response to drought and flood disaster, all enabled by digital twins technology. Conclusions and Prospects The suggestions and trends for development of grain production big data platform are summarized in three aspects: (1) Creating an open, symbiotic grain production big data platform, with core characteristics such as open interface for crop and environmental sensors, maturity grading and a cloud-native packaging mechanism for core algorithms, highly efficient response to data and decision services; (2) Focusing on the typical application scenarios of grain production, take the exploration of technology integration and bi-directional connectivity as the base, and the intelligent service as the soul of the development path for the big data platform research; (3) The data-algorithm-service self-organizing regulation mechanism, the integration of decision-making information with the intelligent equipment operation, and the standardized, compatible and open service capabilities, can form the new quality productivity to ensure food safety, and green efficiency grain production.

Near real-time maize phenology monitoring is crucial for field management,cropping system adjust-ments,and yield estimation.Most phenological monitoring methods are post-seasonal and heavily rely on high-frequency time-series data.These methods are not applicable on the unmanned aerial vehicle(UAV)platform due to the high cost of acquiring time-series UAV images and the shortage of UAV-based phenological monitoring methods.To address these challenges,we employed the Synthetic Minority Oversampling Technique(SMOTE)for sample augmentation,aiming to resolve the small sample mod-elling problem.Moreover,we utilized enhanced"separation"and"compactness"feature selection meth-ods to identify input features from multiple data sources.In this process,we incorporated dynamic multi-source data fusion strategies,involving Vegetation index(VI),Color index(CI),and Texture fea-tures(TF).A two-stage neural network that combines Convolutional Neural Network(CNN)and Long Short-Term Memory Network(LSTM)is proposed to identify maize phenological stages(including sow-ing,seedling,jointing,trumpet,tasseling,maturity,and harvesting)on UAV platforms.The results indi-cate that the dataset generated by SMOTE closely resembles the measured dataset.Among dynamic data fusion strategies,the VI-TF combination proves to be most effective,with CI-TF and VI-CI combinations following behind.Notably,as more data sources are integrated,the model's demand for input features experiences a significant decline.In particular,the CNN-LSTM model,based on the fusion of three data sources,exhibited remarkable reliability when validating the three datasets.For Dataset 1(Beijing Xiaotangshan,2023:Data from 12 UAV Flight Missions),the model achieved an overall accuracy(OA)of 86.53％.Additionally,its precision(Pre),recall(Rec),F1 score(F1),false acceptance rate(FAR),and false rejection rate(FRR)were 0.89,0.89,0.87,0.11,and 0.11,respectively.The model also showed strong gen-eralizability in Dataset 2(Beijing Xiaotangshan,2023:Data from 6 UAV Flight Missions)and Dataset 3(Beijing Xiaotangshan,2022:Data from 4 UAV Flight Missions),with OAs of 89.4％and 85％,respectively.Meanwhile,the model has a low demand for input features,requiring only 54.55％(99 of all features).The findings of this study not only offer novel insights into near real-time crop phenology monitoring,but also provide technical support for agricultural field management and cropping system adaptation.

Real-time crop phenological information can provide crucial guidance for field management, agricultural machinery scheduling, and other agricultural activities. However, in previous research, phenological monitoring is often done post-seasonally, which typically entails a certain degree of lag. To overcome this, here we combined time-series UAV data, image-derived structural information, and cumulative temperature required for maize growth to explore the mapping relationships between multiple data and maize phenology (Bundessortenamt and CHemical Industry scale, BBCH). Then we developed a model for phenology’s real-time monitoring for applications requiring only single-time-phase UAV imagery and a single environmental factor (cumulative temperature). Specifically, a composite index was built using the one-to-one multiplication of vegetation index (VI), structural features (SF), and relative growing degree-days (RGS). Finally, the real-time monitoring model of maize BBCH was constructed via the ordinary least squares (OLS) fitting method. The results reveal the DATT-RGS model performs best, showing significant advantages over other combinations (VI-PH, VI-CC, CC-RGS, and PH-RGS), with R2, RMSE, NRMSE, and RMSEd values of 0.92, 7.66, 13.57, and 38.14 d, respectively. Plant phenology is a combined response outcome to genotype, field management, and regional environment; and while a VI can indicate the maize genotype and mode of field management, cumulus temperature is indicative of the regional environment and hence more mechanistic. Moreover, fluctuations in the sowing date had less of an effect on VI-RGS. However, when meteorological data is unavailable, the VI-PH model is recommended. Further, the VI-RGS model is able to determine the phenological differences and growth rates of maize in various breeding plots. This study presents new insights for the real-time monitoring of phenology from single-time-phase UAV imagery, providing timely crop phenotypic information for enhancing maize field management and smart breeding. The findings also offer technical support for the identification and selection of maize varieties.

Timely and accurate estimation of crop yield and quality can provide a practical and effective basis for the formulation of national food policies. Based on remote sensing data of rice multi-growth stages from 2021 to 2022 in Ninghe District of Tianjin, the methods coupling hierarchical linear model (HLM) with typical vegetation indices and meteorological data were used to estimate yield and quality in rice. The results showed that: (1) Compared with the multiple linear regression model, the methods of estimating rice yield and quality based on HLM had higher stability in interannual expansion; (2) For the three growth stages of rice, namely, jointing, booting and filling stage, the hierarchical linear model of yield and quality estimation at booting stage showed the highest performance. The R<^>2 of the GRVI rice yield estimation model, MSR rice amylose content estimation model, and RDVI rice protein content estimation model were 0.52, 0.70, and 0.88, and RMSE were 1.17 t/ha, 0.85 %, and 0.33 %, respectively. The nRMSE was 11.06 %, 4.46 %, and 3.37 %, respectively. The HLM rice yield and quality estimation models based on multi-growth period data were further established. The GCI rice yield estimation model, MSR amylose content estimation model, and DVI protein content estimation model R<^>2 were 0.67, 0.75, and 0.91, and RMSE were 1.01 t/ha, 0.78 %, and 0.30 %. The nRMSE was 9.48 %, 4.07 %, and 3.05 %. It indicates that the method using HLM has a good potential for accessing yield and quality in rice and shows better scalability at interannual and regional scales.

Vapor pressure deficit (VPD) shows significant spatial and temporal variability in the context of global climate change, which is important for studying the implications of climate change on the structure and function of ecosystems to analyze the effects of VPD on vegetation dynamics. Spatial patterns of vegetation sensitivity to VPD have been recently investigated, however, the feedback of different vegetation types to VPD may vary depending on physiological characteristics, it is unclear how different types influence the sensitivity to VPD. In this study, the ERA5-Land reanalysis time-series dataset was used to analyze the spatial and temporal trends of VPD under different vegetation types. It was found that VPD showed an increasing trend in vegetated areas over the past 20 years with large spatial heterogeneity, generally increasing with drying conditions. On this basis, the spatial patterns of vegetation sensitivity to VPD and temporal trends in sensitivity were evaluated over the past 20 years in China using the enhanced vegetation index (EVI) and near-infrared reflectance of vegetation (NIRv) which can describe vegetation dynamics. The results show that the sensitivities under the two indices have high spatial consistency, with northeastern and central China showing positive sensitivities and southern China showing negative sensitivities, respectively. The positive sensitivities are relatively high for Deciduous Broadleaf Forests (DBF), Deciduous Needleleaf Forests (DNF), Grasslands (GL), and Croplands (CL) types, while the negative sensitivities are larger for Shrublands (SL) and Savannas (SA) types. Under different climatic zones, the sensitivity of CL and GL are independent of climatic zones (both showing positive), while the sensitivity of SL is negative in the Humid zone and positive in the Semi-Arid zone. Temporally, the sensitivity showed a slow increasing trend over the last 20 years. In terms of vegetation types, sensitivities of Evergreen Broadleaf Forests (EBF), DBF, GL and CL types showed a significant increasing trend (p < 0.05), except for the SL type, which showed a significant decreasing trend (p < 0.05). The trends of sensitivity are not affected by the differences in vegetation types (all of them show an increasing trend) under arid and semi-arid conditions, while dry sub-humid and humid have a greater impact on sensitivity trends. The finding of an overall increase in sensitivity suggests a mechanism of erratic change in vegetation growth under climate change. Notably, the increased sensitivity of certain vegetation types (especially GL and CL) suggests that these may become progressively vulnerable to increased VPD as global climate change persists, with the risk of moving from facilitation to inhibition of photosynthesis.

The characteristic coefficient of vertical leaf nitrogen (N) profile is a canopy parameter that indicates the attenuation steepness of leaf N from the top of canopy downward. It is sensitive not only to crop production, grain yield and quality, and light- and N-use efficiency but also to N deficiency in the crop. We introduce this coefficient by exploring a robust method to estimate it from canopy spectral reflectance. We analyze comprehensively various approaches based on diverse datasets of winter wheat. We test and compare the accuracy and stability of models by using the adjusted and weighted coefficient of determination (wRadj2), the mean absolute error (MAE), and the mean and coefficient of variation (CV) over multiple seasons. The analysis focuses mainly on the coefficient of mass-based leaf N profile (Km); nevertheless, a comparison with the coefficient of area-based leaf N profile is presented. The results indicate that the most robust model to estimate Km of winter wheat is Km=(1.8037RGVI-0.9702+0.0786exp(0.6315/DASF))/2, where RGVI is the red and green ratio vegetation index, and DASF is the directional area scattering factor. The mean wRadj2 is 0.663 with CV = 8.2% and the mean MAE is 0.117 with CV = 12.8% over three seasons including various situations. This makes it possible to assess Km at large areas and follow its dynamics over multiple periods in a timely and nondestructive manner.

Nitrogen (N) is one of the most important nutrient matters for crop growth and has the marked influence on the ultimate formation of yield and quality in crop production. As the most mobile nutrient constituent, N always transfers from the bottom to top leaves under N stress condition. Vertical gradient changes of leaf N concentration are a general feature in canopies of crops. Hence, it is significant to effectively acquire vertical N information for optimizing N fertilization managements. Especially, if crop growth status in the middle and bottom leaf layers can be detected early, optimal N utilization might come true. So, it is critical to obtain N vertical information especially in lower leaf layers for accurate evaluation of N nutrient status in winter wheat and timely N recommendation. The rapid detection of vertical N information is difficult by conventional ways. Spectral detecting, especially hyperspectral remote sensing with hundreds of very narrow spectral bands plays a unique role in determining crop biochemical parameters including N status thanks to the notable characteristics of non-destruction and quickness. This technique contributes to the development of fertilizer recommendations and is likely to avoid both the environmental pollution of excessive N fertilization and the effects of N-deficiency in crops. The paper aimed at the relationships between canopy hyperspectral reflectance and N estimation at the different layers of winter wheat canopy and developed a method to estimate N status in different leaf layers of winter wheat canopies. This study used the field data from anthesis of winter wheat in 2016 and coupled a mathematical algorithm, OWC (optimal weight combination) with hyperspectral reflectance to estimate N concentration in different leaf layers of winter wheat. The results showed that OWC yielded $\mathrm{R}^{2}$ values of 0.45, 0.59, 0.25, 0.43 for the first, second, third and fourth leaf from top to bottom in wheat canopies, respectively. So, it is feasible to use canopy hyperspectral information to evaluate the vertical N status in winter wheat canopies, which is promising for optimizing N use by detecting N status in lower leaf layers of crop canopies.

Plant nitrogen content (PNC) is an essential indicator of crop growth and nitrogen nutrition status. Therefore, accurate and efficient access to PNC information is vital for dynamically monitoring potato growth and proper N fertilizer application. In this study, the UAV hyperspectral images were obtained at the budding stage, tuber formation stage, tuber growth stage, starch accumulation stage, and maturity stage of the potato. After preprocessing, the original canopy spectrum and first-order differential spectrum of five growth stages were extracted; Secondly, the correlation analysis was carried out between the extracted canopy spectrum and potato PNC, and the sensitive wavelength of PNC was screened out; Then, the texture and color of two image features of the hyperspectral image at the wavelength of the original spectral features of the canopy were extracted using the gray co-generation matrix and the 1st to 3rd-order color moments, respectively, and the extracted features were correlated with the potato PNC to filter out the top five image features with higher correlation; Finally, based on spectral features, image features, and map fusion features, potato PNC estimation models were established by using elastic network regression (ENR), Bayesian linear regression (BLR), and limit learning machine (ELM). The results showed that: (1) there are differences in the characteristic wavelengths of canopy spectra in the five growth stages of potatoes. Still, most of them were located in the visible region. (2) The correlation between the texture and color characteristics of the original spectral characteristic wavelength image of the canopy and PNC was high. The correlation from the budding stage to the starch store stage was significantly higher than that in the mature stage. (3) The estimation models of potato PNC based on a single spectral feature and a single image feature have a good effect from the budding stage to the starch accumulation stage but a poor effect at the maturity stage. (4) From the budding stage to the starch accumulation stage, the estimation effect of potato PNC based on the map fusion feature was significantly better than the single spectral feature and the single image feature. (5) In each growth period of potato, the PNC estimation models constructed by ENR based on the same variable were better, BLR was the second, and ELM was poor. Among them, the accuracy and stability of the PNC estimation models constructed by ENR with fusion characteristics as model variables were the best. The modeling R2 of five growth periods were 0.91, 0.75, 0.82, 0.77 and 0.69 respectively; RMSE were 0.24%, 0.31%, 0.26%, 0.22% and 0.29% respectively, and NRMSE were 6.59%, 9.79%, 9.58%, 7.87% and 11.03% respectively. This study can provide a fast and efficient technical tool for monitoring the nitrogen nutrition of potatoes.

The resulting maps of land use classification obtained by pixel-based methods often have salt-and-pepper noise, which usually shows a certain degree of cluttered distribution of classification image elements within the region. This paper carries out a study on crop classification and identification based on time series Sentinel images and object-oriented methods and takes the crop recognition and classification of the National Modern Agricultural Industrial Park in Jalaid Banner, Inner Mongolia, as the research object. It uses the Google Earth Engine (GEE) cloud platform to extract time series Sentinel satellite radar and optical remote sensing images combined with simple noniterative clustering (SNIC) multiscale segmentation with random forest (RF) and support vector machine (SVM) classification algorithms to classify and identify major regional crops based on radar and spectral features. Compared with the pixel-based method, the combination of SNIC multiscale segmentation and random forest classification based on time series radar and optical remote sensing images can effectively reduce the salt-and-pepper phenomenon in classification and improve crop classification accuracy with the highest accuracy of 98.66 and a kappa coefficient of 0.9823. This study provides a reference for large-scale crop identification and classification work.

The normalized difference vegetation index (NDVI) is crucial to many sustainable agricultural practices such as vegetation monitoring and health evaluation. However, optical remote sensing data often suffer from a large amount of missing information due to sensor failures and harsh atmospheric conditions. The synthetic aperture radar (SAR) offers a new approach to filling in missing optical data based on its excessive revisit density and its potential to image without interference from clouds and rain. Due to the difference in imaging mechanisms between SAR and optical sensors, it is very difficult to fuse the data. This paper developed an advanced deep learning Spatio-temporal fusion method, i.e., Transformer Temporal-spatial Model (TTSM), to synergize the SAR and optical time-series to reconstruct vegetation NDVI time series in cloudy regions. The proposed multi-head attention and end-to-end architecture achieved satisfactory accuracy (R-2 greater than 0.88), outperforming the existing deep learning solutions. Extensive experiments were carried out to evaluate the TTSM method on large-scale areas (the spatial scale of megapixels) in northeast China with the main vegetation types of crops and forests. The R-2, SSIM, RMSE, NRMSE, and MAE of our prediction results were 0.88, 0.80, 0.06, 0.16, and 0.05, respectively. The influence of training sample size was investigated through a transfer learning study, and the result indicated that the model had good generalizability. Overall, our proposed method can fill in the gap of optical data at an extensive regional scope over the vegetated area using SAR.

The Loess Plateau is a typical ecologically sensitive area that can easily be perturbed by the effects of human activities and global climate change. Therefore, it is necessary to develop tools to monitor the environmental quality in the LP quickly and accurately. To reveal the spatio-temporal changes in environmental quality in the LP from 2000 to 2020, we used the Moderate-Resolution Imaging Spectroradiometer (MODIS) products on the Google Earth Engine platform and constructed the remote sensing ecological index (RSEI) through principal component analysis (PCA). Then, Sen–Mann–Kendall methods were applied to determine the changing trend of the environmental quality of the LP. Finally, natural and anthropogenic factors affecting the environmental quality were probed using a geographical detector model. The results showed that: (1) the average RSEI values in 2000, 2010 and 2020 were 0.396, 0.468 and 0.511, respectively, displaying an upward trend from 2000 to 2020, with a growth rate of 0.005 year−1. The overall environment quality was moderate (0.4–0.6). (2) In terms of spatial distribution, the environmental quality was excellent in the southeast and poor in the northwest of the LP. The areas with improved environmental quality (84.51%) were located in all the counties, whereas the areas with degraded environmental quality (8.11%) occurred in the north and southeast of the study area. (3) Greenness, heat, wetness, dryness and land use types were prominent factors affecting RSEI throughout the study period; additionally, the total industrial gross domestic product showed a growing influence. The contribution of multi-factor interaction was stronger than that of single factors. The results will provide a reference and a new research perspective for local environmental protection and regional planning.

土壤有机质含量是耕地质量定级的依据,是耕地质量评价的核心内容之一,因此,精准高效地获取土壤有机质含量非常重要.高分辨率遥感技术和谷歌地球引擎(Google Earth Engine,GEE)云计算平台的出现,为土壤有机质的高效反演提供了新的途径和方法.该研究以藁城区的Sentinel-2A MSI数据和Landsat8 OLI数据为主要的数据源,结合Sentinel-1 SAR数据、ECMWF/ERA5气象数据和USGS/SRTMGL1_003高程数据,分别采用随机森林(Random Forest,RF)、梯度升级树(Gradient Boosting Decision Tree,GBDT)和支持向量机(Support Vector Machine,SVM)算法,在GEE平台对藁城耕地土壤有机质含量进行反演.结果表明:1)基于Sentinel-2A建立的模型(模型A*)在预测SOM含量方面优于基于Landsat8建立的模型(模型B*),GBDT算法下的Sentinel-2A的全变量模型取得了最佳结果(R2=0.759,RMSE=2.852 g/kg);2)考虑红边波段的Sentinel-2A数据建立的模型(A-1)比不考虑红边波段的模型(A-0),R2提高了9.752％;;3)从不同的预测算法来看,GBDT算法能较好地适用于研究区的土壤有机质预测,GBDT算法、Sentinel-2A与GEE的结合是土壤有机质预测制图的一种有效方法.

The first flowering date (FFD) is a critical phenological parameter closely related to the apple yield, so the ac-curate prediction of the FFD is important for precise orchard production management. Existing methods to predict the FFD are mostly based on air temperature (Ta) measured at meteorological stations, but to great differences in meteorological variations and the ecological conditions, these methods cannot present the dif-ferences of FFD under complex meteorological conditions and provide spatially continuous FFD information at the level of a region. Therefore, we propose a method to predict spatially continuous apple FFD from remote sensing land surface temperature (LST) based on flowering prediction model. Firstly, the missing LST data were reconstructed by using spatio-temporal reconstruction (STR) approach developed. Next, new air temperature (NAT) data were generated by using the daily Ta estimation (DTE) model and the reconstructed LST. Finally, apple FFD was predicted by the NAT data and the apple flowering prediction model established based on random forest (RF) algorithm and the phenology sequential model, and the prediction accuracy was verified by com-parison with the independently measured apple FFD. The LST reconstructed by using the STR approach has mean absolute error (MAE) ranging from 0.51 to 0.68 degrees C, and root mean square error (RMSE) ranging from 1.07 to 1.21 degrees C. The MAE between the NAT data and the High-Resolution Land Surface Data Assimilation System (HR-CLDAS) meteorological data ranges from 2.15 to 3.23 degrees C, and the RMSE ranges from 2.81 to 4.27 degrees C. In addition, the determination coefficient (R2) and RMSE between the predicted and measured FFD is 0.72 and 2.96 days, respectively. These results demonstrate that the developed method maximizes the potential of MODIS LST in predicting spatially continuous apple FFD, which is valuable for flower and fruit thinning, to defend against frost disasters, and in general for refined orchard production management.

Above-ground biomass (AGB) is an important indicator for monitoring crop growth and plays a vital role in guiding agricultural management, so it must be determined rapidly and nondestructively. The present study investigated the extraction from UAV hyperspectral images of multiple variables, including canopy original spectra (COS), first-derivative spectra (FDS), vegetation indices (VIs), and crop height (CH) to estimate the potato AGB via the machine-learning methods of support vector machine (SVM), random forest (RF), and Gaussian process regression (GPR). High-density point clouds were combined with three-dimensional spatial information from ground control points by using structures from motion technology to generate a digital surface model (DSM) of the test field, following which CH was extracted based on the DSM. Feature bands in sensitive spectral regions of COS and FDS were automatically identified by using a Gaussian process regression-band analysis tool that analyzed the correlation of the COS and FDS with the AGB in each growth period. In addition, the 16 Vis were separately analyzed for correlation with the AGB of each growth period to identify highly correlated Vis and excluded highly autocorrelated variables. The three machine-learning methods were used to estimate the potato AGB at each growth period and their results were compared separately based on the COS, FDS, VIs, and combinations thereof with CH. The results showed that (i) the correlations of COS, FDS, and VIs with AGB all gradually improved when going from the tuber-formation stage to the tuber-growth stage and thereafter deteriorated. The VIs were most strongly correlated with the AGB, followed by FDS, and then by COS. (ii) The CH extracted from the DSM was consistent with the measured CH. (iii) For each growth stage, the accuracy of the AGB estimates produced by a given machine-learning method depended on the combination of model variables used (VIs, FDS, COS, and CH). (iv) For any given set of model variables, GPR produced the best AGB estimates in each growth period, followed by RF, and finally by SVM. (v) The most accurate AGB estimate was achieved in the tuber-growth stage and was produced by combining spectral information and CH and applying the GPR method. The results of this study thus reveal that UAV hyperspectral images can be used to extract CH and crop-canopy spectral information, which can be used with GPR to accurately estimate potato AGB and thereby accurately monitor crop growth.