Search Results (105)

The salinization of agricultural soils is a serious threat to farming and ecological balance in arid and semi-arid regions. Accurate estimation of soil water-soluble ions (calcium, carbonate, magnesium, and sulfate) is necessary for correct monitoring of soil salinization and sustainable land management. Hyperspectral ground-based data are valuable in soil salinization monitoring, but the acquisition cost is high, and the coverage is small. Therefore, this study proposes a two-stage deep learning framework with multispectral remote-sensing images. First, the wavelet transform is used to enhance the Transformer and extract fine-grained spectral features to reconstruct the ground-based hyperspectral data. A comparison of ground-based hyperspectral data shows that the reconstructed spectra match the measured data in the 450–998 nm range, with R² up to 0.98 and MSE = 0.31. This high similarity compensates for the low spectral resolution and weak feature expression of multispectral remote-sensing data. Subsequently, this enhanced spectral information was integrated and fed into a novel multiscale self-attentive Transformer model (MSATransformer) to invert four water-soluble ions. Compared with BPANN, MLP, and the standard Transformer model, our model remains robust across different spectra, achieving an R² of up to 0.95 and reducing the average relative error by more than 30%. Among them, for the strongly responsive ions magnesium and sulfate, R² reaches 0.92 and 0.95 (with RMSE of 0.13 and 0.29 g/kg, respectively). For the weakly responsive ions calcium and carbonate, R² stays above 0.80 (RMSE is below 0.40 g/kg). The MSATransformer framework provides a low-cost and high-accuracy solution to monitor soil salinization at large scales and supports precision farmland management. Full article

With the swift progression of the High-Standard Farmland Construction Program in China and worldwide, many dryland wheat fields can be irrigated once during the wheat growth stage (one-off irrigation). However, the combined strategies of one-off irrigation, tillage, and N management for augmenting wheat grain yield and quality are still undeveloped in drought regions. Two-site split–split field experiments were conducted to study the impacts of irrigation, tillage, and N management and their combined effects on grain yield; the contents of protein and protein components; processing quality; and the characteristics of N accumulation and translocation in wheat from a typical dryland wheat production area in China from 2020 to 2022. The irrigation practices (I0, zero irrigation and I1, one-off irrigation), tillage methods (RT, rotary tillage; PT, plowing; and SS, subsoiling) and N management (N0, N120, N180, and N240) were applied to the main plots, subplots and sub-subplots, respectively. The experimental sites, experimental years, irrigation practices, tillage methods, and N management methods and their interaction significantly affected the yield, quality, and plant N characteristics of wheat in most cases. Compared to zero irrigation, one-off irrigation significantly increased the plant N accumulation, enhancing grain yield by 33.7% while decreasing the contents of total protein, albumin, globulin, gliadin, and glutenin by 4.4%, 6.4%, 8.0%, 12.2%, and 10.0%, respectively. It also decreased the wet gluten content, stability time, sedimentation value, extensibility by 4.1%, 10.7%, 9.7%, and 5.5%, respectively, averaged across sites and years. Subsoiling simultaneously enhanced the aforementioned indicators compared to rotary tillage and plowing in most sites and years. With the increase in N rates, wheat yield firstly increased and then decreased under zero irrigation combined with rotary tillage, while it gradually increased when one-off irrigation was combined with subsoiling; however, the contents of total protein and protein components and the quality tended to increase firstly and then stabilize regardless of irrigation practices and tillage methods. The correlations of yield and quality indicators with plant N characteristics were negative when using distinct irrigation practices and tillage methods, while they were positive under varying N management. The decrease in wheat quality induced by one-off irrigation could be alleviated by optimizing N management. I1STN180 exhibited higher yield, plant N accumulation and translocation, and better quality in most cases; thus, all metrics of wheat quality were significantly increased, with a yield enhancement of 50.3% compared to I0RTN180. Therefore, one-off irrigation with subsoiling and an N rate of 180 kg ha⁻¹ is an optimal strategy for high yield, high protein, and high quality in dryland wheat production systems where one-off irrigation is assured. Full article

High-standard farmland fertility enhancement projects can lead to the sustainable utilization of arable land resources. However, due to difficulties in project implementation and uncertainties in costs, resource allocation efficiency is constrained. To address these challenges, this study first analyzes the impact of geography and engineering characteristics on cost indicators and applies principal component analysis (PCA) to extract key influencing factors. A hybrid prediction model is then constructed by integrating the Northern Goshawk Optimization (NGO) algorithm with a Backpropagation Neural Network (BP). The NGO–BP model is compared with the RF, XGBoost, standard BP, and GA–BP models. Using data from China’s 2025 high-standard farmland fertility enhancement projects, empirical validation shows that the NGO–BP model achieves a maximum RMSE of only CNY 98.472 across soil conditioning, deep plowing, subsoiling, and fertilization projects—approximately 30.74% lower than those of other models. The maximum MAE is just CNY 88.487, a reduction of about 32.97%, and all R² values exceed 0.914, representing an improvement of roughly 5.83%. These results demonstrate that the NGO–BP model offers superior predictive accuracy and generalization ability compared to other approaches. The findings provide a robust theoretical foundation and technical support for agricultural resource management, the construction of projects, and project investment planning. Full article

Soil heavy metal pollution threatens agricultural safety and human health, with Cd exceeding standards being the most common problem in contaminated farmland. The development of hyperspectral remote sensing technology has provided a novel methodology of quickly and non-destructively monitoring heavy metal contamination in soil. This study aims to explore the potential of an interpretable Stacking ensemble learning model for the estimation of soil Cd contamination in farmland hyperspectral data. We assume that this method can improve the modeling accuracy. We chose Zhangjiagang City, Jiangsu Province, China, as the study area. We gathered soil samples from wheat fields and analyzed soil spectral data and Cd level in the lab. First, we pre-processed the spectra utilizing fractional-order derivative (FOD) and standard normal variate (SNV) transforms to highlight the spectral features. Second, we applied the competitive adaptive reweighted sampling (CARS) feature selection algorithm to identify the significant wavelengths correlated with soil Cd content. Then, we constructed and compared the estimation accuracy of multiple machine learning models and a Stacking ensemble learning method and utilized the Optuna method for hyperparameter optimization. Ultimately, the SHAP method was used to shed light on the model’s decision-making process. The results show that (1) FOD can further highlight the spectral features, thereby strengthening the correlation between soil Cd content and wavelength; (2) the CARS algorithm extracted 3.4–6.8% of the feature wavelengths from the full spectrum, and most of them were the wavelengths with high correlation with soil Cd; (3) the optimal estimation precision was achieved using the FOD1.5-SNV spectral pre-processing combined with the Stacking model (R² = 0.77, RMSE = 0.05 mg/kg, RPD = 2.07), and the model effectively quantitatively estimated soil Cd contamination; and (4) SHAP further revealed the contribution of each base model and characteristic wavelengths in the Stacking modeling process. This research confirms the advantages of the interpretable Stacking model in hyperspectral estimation of Cd contamination in farmland wheat soil. Furthermore, it offers a foundational reference for the future implementation of quantitative and non-destructive regional monitoring of heavy metal contamination in farmland soil. Full article

Identifying the soil quality and the sources of heavy metals in the production areas of characteristic agricultural products is crucial for ensuring the quality of such products and the sustainable development of agriculture. This research took the farmland soil of Luzuo Town, a characteristic production area of Cangshan garlic in Linyi City, as the research object. The contents of Cr, Cu, Ni, Pb, Zn, As, Hg, and Cd in farmland soil were analyzed. The ecological risks were evaluated using the Geographical Cumulative Index (I_geo) and the Potential Ecological Risk Index. The spatial distribution characteristics of the elements were determined through geostatistical analysis, and Positive Matrix Factorization (PMF) was used for source apportionment. The results show the following: (1) The average concentrations of all heavy metals exceeded local background values, with Cr and Hg surpassing the screening thresholds from China’s “Soil Pollution Risk Control Standards” (GB 15618-2018). (2) The results of the Moran’s index show that, except for Hg and Cd, all the elements had a high spatial autocorrelation, and there are two potential highly polluted areas in the study area. (3) Soils were generally uncontaminated or low risk, with Hg and Cd as the primary ecological risk contributors. (4) Five sources were quantified: fertilizer and pesticide sources (32.28%); mixed sources of fertilizer, pesticides, and manure (14.15%); mixed sources of traffic activities and agricultural waste discharge (19.95%); natural sources (20.55%); and incineration sources (13.07%). This study demonstrates the value of integrating geospatial and statistical methods for soil pollution management. Targeted control of Hg/Cd and reduced agrochemical use are recommended to protect this important agricultural region. Full article

China faces the dual challenges of mitigating greenhouse gas emissions and ensuring food security. Given that crop cultivation constitutes a major source of agricultural greenhouse gas emissions, analyzing the emission reduction impact of China’s high-standard farmland construction (HSFC) policy, a crucial food security initiative, holds significant importance. This study calculates greenhouse gas emissions from crop cultivation (CGHGE) from a life cycle assessment (LCA) perspective and evaluates the agricultural new-quality productivity level across 31 regions in China from 2005 to 2022. Subsequently, this study utilizes the continuous difference-in-differences (DID) model to examine the impact of the HSFC policy on CGHGE per unit area. Furthermore, the mediating role of agricultural new-quality productivity in the relationship between HSFC policies and CGHGE per unit area was examined. The results show that HSFC can significantly mitigate the growth of CGHGE per unit area, with an average annual reduction of 62.88%. The regional heterogeneity analysis indicates that HSFC exerts statistically significant negative effects on CGHGE per unit area across both western and eastern China. Furthermore, heterogeneity tests demonstrate that HSFC’s emission reduction effects are particularly pronounced in major grain-producing regions. HSFC contributes to emission reductions by enhancing agricultural new-quality productive forces, which subsequently lead to lower CGHGE. The findings of this study suggest that governments should implement differentiated and targeted policies for HSFC, with particular emphasis on the crucial role of new-quality agricultural productivity in reducing CGHGE. Full article

This study investigates the impact of China’s construction of high-standard farmland (CHSF) initiatives on grain productivity, focusing on total factor productivity growth of grain (TFPG) from 2000 to 2021. Using a continuous Difference-in-Differences (DID) approach based on balanced panel data from 31 Chinese provinces, this paper identifies significant productivity improvements, with TFPG increasing by an average of 7% post-implementation of CHSF. However, the effects are not uniform across regions—productivity gains are more pronounced in non-major grain-producing and plain areas, emphasizing the role of region-specific infrastructure and adaptive strategies. These findings provide empirical evidence on how large-scale farmland improvement enhances productivity through mechanization and better land use. However, the reliance on provincial-level data may result in localized variations in CHSF implementation being overlooked, suggesting the need for further micro-level analysis. Overall, this study highlights the importance of tailored agricultural policies to enhance their effectiveness and promote agricultural sustainability in China and other developing economies. Full article

Heavy metal pollution refers to the presence of excessive levels of heavy metal elements in soil beyond their natural background concentrations, posing serious threats to human health and ecological systems. Several factors are involved in the contamination disparity in agriculture soils from various terrains, demanding extra care. An examination of the topographical HM dispersions in farmland soils from the Licheng District was conducted to reveal spatial changes in pollution levels and sources and to establish an empirical framework to develop targeted remediation strategies and promote sustainable land management practices. Cd and As had over-standard rates of more than 50% in the low-lying area, whereas the HMs in the high-lying area had over-standard rates of more than 50%. Also, the rates of HMs in high terrain were higher than in low terrain. Using the single-factor pollution index, only low-lying Cu, Ni, Pb, and Hg contamination levels were clean in low-lying and high-lying areas. The overall decline in HM pollution occurred from high to low terrain, triggered by soil physicochemical properties and human interventions. Meanwhile, strong anthropogenic influence fell in high terrain for pollution. Nevertheless, low levels of HM-integrated contamination prevailed in both topographies. Natural and anthropogenic processes gave rise to environmental pollution, such as soil formation, fertilization, metal smelting, and traffic emissions. Overall, the district held a low risk for HMs. The results highlight that strong anthropogenic interventions resulted in increased HM contamination, in addition to natural processes. It is possible to further reduce HM pollution and risk by promoting scientific agricultural techniques, new energy vehicles, and cleaner production. Full article

This study focuses on 67 counties in Guangdong Province, China, and investigates the spatial distribution patterns, regional differentiation characteristics, and functional zoning of rural areas based on the “Production–Living–Ecological” (PLE) functional synergy theoretical framework. Multiple quantitative methods, including the entropy method, spatial concentration degree, and functional identification, were employed. Key findings include: (1) Rural functions in Guangdong exhibit significant heterogeneous evolution. Production functions have generally weakened, showing a spatial pattern of “consolidation in the south and decline in the north”. Ecological functions demonstrate a U-shaped recovery trend, with high-value areas concentrating around the Pearl River Delta urban agglomeration, indicating effective ecological protection policies. Living functions continue to decline due to population mobility and imbalanced public services. (2) Structural transformation of rural function types occurred: Weakly integrated counties decreased (2010–2019), dual function type counties (production–ecological and living–ecological) significantly increased, and ecology-dominant counties predominated, highlighting ecological polarization under policy interventions. (3) Functional evolution is driven by terrain gradients, policy regulation, and industrial relocation. The research provides empirical evidence for optimizing territorial spatial governance and coordinating urban–rural development. Recommendations include promoting dynamic PLE balance through high-standard farmland construction, ecological industrialization cultivation, and cross-regional compensation mechanisms to facilitate rural revitalization and sustainable development. Full article

This study analyzed the changes in landscape patterns and the ecological health status of karst plateau wetlands, providing valuable insights into their conservation. Using land cover data from 1996 to 2021, DEM, and Landsat series satellite imagery, this study employed landscape ecology methods and the pressure–state–response (PSR) model framework. A regional landscape grid was constructed, and 13 indicators were selected to establish an ecological health evaluation system for karst plateau wetlands. This allowed us to explore the spatiotemporal change characteristics of the landscape pattern and the ecological health of karst plateau wetlands. The results showed that over a 25-year period, farmland, grassland, and construction land areas have increased, whereas forested land areas have decreased. Water bodies remained relatively stable but showed a trend of transitioning into grassland. Unused land showed no significant change. Landscape analysis indicated that grasslands experience the highest rate of fragmentation, complex shapes, and greater heterogeneity, whereas water bodies have the lowest fragmentation, more regular shapes, and lower heterogeneity. Other landscape types exhibited moderate characteristics. Overall, the landscape of the study area exhibited high fragmentation, specific patch aggregation, moderate patch density, and low diversity. A comprehensive ecological health evaluation revealed that the wetland health value remained at an “unhealthy” level from 1996 to 2021. Although there was a brief improvement in 2010, effective long-term recovery was not achieved. Spatially, the proportion of “diseased” areas peaked in 2006, and most grid zones remained in an “unhealthy” state over the years, with none reaching the “healthy” standard. These findings highlight the severe challenges faced by the wetland ecosystem. Full article

Accurately and precisely obtaining field crop information is crucial for evaluating the effectiveness of rice transplanter operations. However, the working environment of rice transplanters in paddy fields is complex, and data obtained solely from GPS devices installed on agricultural machinery cannot directly reflect the specific information of seedlings, making it difficult to accurately evaluate the quality of rice transplanter operations. This study proposes a CAD-UNet model for detecting rice seedling rows based on low altitude orthorectified remote sensing images, and uses evaluation indicators such as straightness and parallelism of seedling rows to evaluate the operation quality of the rice transplanter. We have introduced convolutional block attention module (CBAM) and attention gate (AG) modules on the basis of the original UNet network, which can merge multiple feature maps or information flows together, helping the model better select key areas or features of seedling rows in the image, thereby improving the understanding of image content and task execution performance. In addition, in response to the characteristics of dense and diverse shapes of seedling rows, this study attempts to integrate deformable convolutional network version 2 (DCNv2) into the UNet network, replacing the original standard square convolution, making the sampling receptive field closer to the shape of the seedling rows and more suitable for capturing various shapes and scales of seedling row features, further improving the performance and generalization ability of the model. Different semantic segmentation models are trained and tested using low altitude high-resolution images of drones, and compared. The experimental results indicate that CAD-UNet provides excellent results, with precision, recall, and F1-score reaching 91.14%, 87.96%, and 89.52%, respectively, all of which are superior to other models. The evaluation results of the rice transplanter’s operation effectiveness show that the minimum and maximum straightnessof each seedling row are 4.62 and 13.66 cm, respectively, and the minimum and maximum parallelismbetween adjacent seedling rows are 5.16 and 23.34 cm, respectively. These indicators directly reflect the distribution of rice seedlings in the field, proving that the proposed method can quantitatively evaluate the field operation quality of the transplanter. The method proposed in this study can be applied to decision-making models for farmland crop management, which can help improve the efficiency and sustainability of agricultural operations. Full article

At present, with the rapid development of urbanization and industrialization, the contradiction between development and cultivated land protection is exacerbated. Scientifically quantifying ecosystem service value and constructing an ecological compensation mechanism of cultivated land are significant paths for cultivated land protection. This study originates from an extended three-dimensional ecological footprint model, introduces a carbon footprint accounting path, and thoroughly evaluates the sustainable use of farmland ecology. It aimed to accurately calculate the ecosystem service value of farmland, formulate ecological compensation standards, establish an ecological compensation model to measure the total amount of ecological compensation for cultivated land, and delineate the “five-zone map” of ecological compensation for farmland. (1) There is a partial spatial heterotopia phenomenon between ecological consumption and ecological services. (2) In 2022, the ecosystem service value of cultivated land in Shandong Province is high, reaching CNY 78.479 billion. Overall, exported the ecological service value of cultivated land to the outside world. Qingdao, Yantai, and Weihai are farmland ecological compensation zones, with a compensation amount of CNY 71 million. (3) The priority compensation zones are Qingdao and Yantai on the Shandong Peninsula. The priority compensated zones are mainly located in the northern region of Shandong. Exploring ecological compensation for cultivated land ecology at the spatial and temporal scale has important value for ecological protection and security of cultivated land. Full article

Drought, as an extreme climatic event, is considered one of the most severe natural disasters worldwide. In Northeast Asia, the frequency and intensity of drought have been exacerbated by climate change, causing significant negative impacts on the region’s socioeconomic conditions and agricultural production. This study analyzed the spatiotemporal evolution and trends in drought in transboundary river basins in Northeast Asia from 1990 to 2020, using meteorological station data and remote sensing data. The Standardized Precipitation Evapotranspiration Index (SPEI) and Vegetation Condition Index (VCI) were employed to assess drought characteristics, and a comprehensive analysis of the SPEI and VCI indices was conducted to evaluate drought severity under different land cover types. The results indicate that (1) in the past two decades, both the SPEI and VCI indices have shown an increasing trend in the basin, with moderate and mild droughts being predominant. (2) High and extreme droughts mainly occur in forest areas, accounting for 17.91% and 10.76%, respectively, followed by farmland. Full article

Studying the policy effectiveness and impact process of the high-standard farmland construction (HSFC) on the green agricultural development (GAD) provides reference for sustainable development of agriculture. Based on the quasi experimental conditions for the sub regional promotion of China’ s HSFC policy and making use of the balanced panel data from 2004 to 2022 in China, this article diagnoses the level and evolution characteristics of GAD in China, empirically tests the effects of the China’s HSFC policy on the GAD level by the continuous difference-in-differences (DID) model, and then further analyzes the mediating roles of horizontal agricultural production division and land management scale efficiency. The research results indicate that (1) the GAD level of China continues to improve form 2004 to 2022; (2) the HSFC policy has been positively influencing the GAD level, and has gone through a significance level test of 0.01; (3) further study reveals that the HSFC policy promotes the GAD level primarily through the agricultural green technology progress (AGTP) and the agricultural green efficiency change (AGEC), with the AGTP being the main contributor; and (4) the HSFC policy positively influences the GAD level by enhancing horizontal agricultural production division and land management scale efficiency. To improve the level of GAD, it is essential to continuously optimize policy for the HSFC, promote the AGTP and the improvement of the AGEC, and effectively improve the horizontal agricultural production division level and land management scale efficiency. Full article

Given the constraints of limited cultivated land resources, ensuring and enhancing crop productivity are crucial for food security. This study takes Chengdu as a case study. Using the cultivated land productivity (CLP) evaluation model, we calculated the cultivated land productivity index (CLPI) and analyzed its spatial distribution characteristics. The Geographical Detector model was employed to identify the main factors influencing CLP, and corresponding countermeasures and measures were proposed based on the limiting degrees of these factors. The findings reveal that Chengdu’s CLP index ranges from 1231 to 3053. Global spatial autocorrelation analysis indicates a spatial agglomeration pattern in Chengdu’s overall crop productivity distribution. The local spatial autocorrelation analysis demonstrates that township (street)-level crop productivity in Chengdu is primarily characterized by “high–high”, “low–low”, and “low–high” clusters. Key factors influencing the spatial differentiation of CLP in Chengdu include the agronomic management level, soil bulk density, irrigation guarantee rate, soil body configuration, field slope, and farmland flood control standard. Interaction detection shows that there are both double-factor and nonlinear enhancements among the factors. Specifically, the interaction between soil bulk density and the agronomic management level among other factors have the most explanatory power for the spatial differentiation of CLP. The CLP in Chengdu is highly restricted by its technical level, with the agronomic management level severely limiting CLP by more than 50%. These research results provide a theoretical reference for regional high-standard farmland construction and the protection and utilization of cultivated land resources. Full article