Cropland soil organic carbon (SOC) is crucial for global food security and mitigating the greenhouse effect. Accurate SOC prediction using hyperspectral data is essential for dynamic monitoring of soil carbon pools in croplands. However, effective methods to reduce hyperspectral data dimensionality and integrate it with suitable regression algorithms for reliable prediction models are poorly understood. In this study, we analyzed 108 soil samples from Changting County, Fujian Province, China. Our objective was to evaluate the performance of various combinations of six feature selection methods and four regression algorithms for SOC prediction. Our findings are as follows: the combination of the Successive Projections Algorithm (SPA) and Partial Least Squares (PLS) yielded the most favorable results, with R² (0.61), RMSE (1.77 g/kg), and MAE (1.48 g/kg). Moreover, we determined the relative importance of variables, with the following ranking: 696 nm > 892 nm > 783 nm > 1641 nm > 1436 nm > 396 nm > 392 nm > 2239 nm > 2129 nm. Notably, 696 nm exhibited the highest importance in the SPA-PLS model, with the Variable Importance in Projection (VIP) value of 1.22. This study provides profound insights into feature selection methods and regression algorithms for SOC prediction, highlighting the superiority of SPA-PLS as the optimal combination.

Cropland maps at regional or global scales typically have large uncertainty and are also inconsistent with each other. The substantial uncertainty in these cropland maps limits their use in research and management efforts. Many synergy approaches have been developed to generate hybrid cropland maps with higher accuracy from existing cropland maps. However, few studies have compared the advantages, disadvantages, and regional suitability of these approaches. To close this knowledge gap, this study aims to compare two representative synergy methods of cropland mapping: Geographically weighted regression (GWR) and modified fuzzy agreement scoring (MFAS). We assessed how the sample size, quality of input satellite-based maps, and various landscapes influence the accuracy of the synergy maps based on these two methods. The GWR model is a regression analysis predominantly dependent on the cropland percentage of the training samples, while the MFAS method is largely influenced by the consistency of input datasets, and the training samples only play an auxiliary role. Therefore, the GWR method was relatively more sensitive to the number of training samples than the MFAS method. The quality of input maps had a significant impact on both methods, particularly on MFAS. In regions with heterogeneous landscapes and high elevations, the croplands are generally more fragmented, and the consistency of the input satellite-based maps was lower; the application of cropland percentage samples could compensate for the low dataset consistency. Therefore, GWR is more suitable for regions with heterogeneous landscapes, while MFAS is more appropriate for regions with homogeneous landscapes. The MFAS method uses cropland area from the agricultural statistics to calibrate the initial synergy maps, while the GWR model only considers the spatial distribution of cropland and does not make use of the distribution information of cropland area. The MFAS method showed a higher correlation with the statistical data, while GWR model exhibited a stronger relationship with cropland percentage. Our study reveals the advantages, disadvantages, and regional suitability of the two main types of synergy methods (regression analysis methods and data consistency scoring methods) and can inform future synergy cropland mapping efforts.

Spring frost is an extreme temperature event that poses a significant threat to winter wheat production and consequently jeopardizes food security. In the context of climate change, the accelerated phenology of winter wheat due to global warming advances the frost-sensitive stage, thereby escalating the risk of spring frost damage. Present techniques for monitoring and assessing frost damage heavily rely on meteorological data, controlled field experiments and crop model simulations, which cannot accurately depict the actual disaster situation for winter wheat. In this study, we propose a novel method that utilizes remote sensing index and statistical data to ascertain the spatial distribution of spring frost damage to winter wheat and evaluate the extent of damage. This method was employed to monitor and assess the spring frost damage event that occurred in Shandong province from 3 to 7 April 2018. The result shows that beginning on 3 April, the daily minimum temperature in western Shandong Province dropped significantly (decreased by 17.93 °C), accompanied by precipitation. The daily minimum temperature reached the lowest on 7 April (−1.48 °C). The growth of winter wheat began to be inhibited on 3 April 2018, and this process persisted until 13 April. Subsequently, the impact of spring frost damage on winter wheat ceased and growth gradually resumed. The affected area of winter wheat spanned 545,000 mu with an accuracy rate of 89.72%. Severely afflicted areas are mainly located in the cities of Jining, Zaozhuang, Dezhou, Heze, Liaocheng, Jinan and Tai’an in western Shandong province, and the yield reduction rates were 5.27~12.02%. Our monitoring results were consistent with the distribution of county-level winter wheat yield in 2018 in Shandong province, the daily minimum temperature distribution during spring frost and severely afflicted areas reported by the news. This method proves effective in delineating the spatial distribution of agricultural disasters and monitoring the extent of disaster damage. Furthermore, it can provide reliable information of disaster area and geospatial location for the agricultural department, thereby aiding in disaster damage assessment and post-disaster replanting.

Given the increasing crop yield losses, water scarcity, and fertilizer application in Northeast China, a systematic assessment is increasingly necessary to investigate the potential of crop redistribution to enhance grain production while alleviating environmental pressures. Here we quantify the potential of crop redistribution in Northeast China through a multi-objective optimization approach. First, we construct a dataset that contains four objectives including crop yield, yield losses, water deficit, and nitrogen fertilizer application based on their annual data in 273 counties over two decades (2001–2020). Second, we optimize the county-level distribution of rice, maize and soybean using the developed dataset and evaluate the benefits on each objective. Finally, we design a crop redistribution scheme and analyze its impact on the cropping structure in Northeast China based on the optimal solution. Results show significant potential of crop redistribution, with crop production increases by 1.70% (2.41 × 10⁶ tons), production losses decrease by 2.69% (1.84 × 10⁵ tons), water deficit decreases by 6.78% (3.88 × 10⁸ m³) and N fertilizer application decreases by 10.87% (5.41 × 10⁷ kg) when all the objectives are optimized simultaneously. The crop redistribution scheme is summarized as follows: compared with the baseline crop structure, rice area increases by 69.58%, maize reduces by 12.8%, and soybean reduces by 54.79% in Northeast China. Specifically, rice area increases in northwestern Heilongjiang, eastern Jilin, most counties in Liaoning, and reduces elsewhere. Maize area reduces in most of the counties, except for several counties in southwestern Heilongjiang, northern Jilin, and northern parts of the Four Eastern Leagues. Soybean area reduces in northern part of Heilongjiang and Four Eastern Leagues and increases in western Jilin and most counties in Liaoning. Although crop redistribution scheme was generated, the model remains limited in terms of crop types, spatial resolution, and the range of factors influencing crop distribution. Future work will address these limitations to enhance the reliability and applicability of the crop redistribution model.

Monitoring vegetation productivity at extremely fine resolutions is valuable for real-world agricultural applications, such as detecting crop stress and providing early warning of food insecurity. Solar-Induced Chlorophyll Fluorescence (SIF) provides a promising way to directly measure plant productivity from space. However, satellite SIF observations are only available at a coarse spatial resolution, making it impossible to monitor how individual crop types or farms are doing. This poses a challenging coarsely-supervised regression (or downscaling) task; at training time, we only have SIF labels at a coarse resolution (3km), but we want to predict SIF at much finer spatial resolutions (e.g. 30m, a 100x increase). We also have additional fine-resolution input features, but the relationship between these features and SIF is unknown. To address this, we propose Coarsely-Supervised Smooth U-Net (CS-SUNet), a novel method for this coarse supervision setting. CS-SUNet combines the expressive power of deep convolutional networks with novel regularization methods based on prior knowledge (such as a smoothness loss) that are crucial for preventing overfitting. Experiments show that CS-SUNet resolves fine-grained variations in SIF more accurately than existing methods.