Search citation statements
Paper Sections
Citation Types
Year Published
Publication Types
Relationship
Authors
Journals
The accurate prediction of the spatial variability for soil water content (SWC) in farmland is essential for water resource management and sustainable agricultural development. However, natural factors introduce uncertainty and result in poor alignment when predicting farmland SWC, leading to low accuracy. To address this, this study introduced a novel indicator: landscape indices. These indices include the largest patch index (LPI), edge density (ED), aggregation index (AI), patch cohesion index (COH), contagion index (CON), landscape division index (DIV), percentage of like adjacencies (PLA), Shannon evenness index (SHEI), and Shannon diversity index (SHDI). A Bayesian optimization–deep forest (BO–DF) model was developed to leverage these indices for predicting the spatial variability of SWC. Statistical analysis revealed that landscape indices exhibited skewed distributions and weak linear correlations with SWC (r < 0.2). Despite this, incorporating landscape index variables into the BO–DF model significantly improved prediction accuracy, with R2 increasing by 35.85%. This model demonstrated a robust nonlinear fitting capability for the spatial variability of SWC. Spatial mapping of SWC using the BO–DF model indicated that high-value areas were predominantly located in the eastern and southern regions of the Yellow River Delta in China. Furthermore, the SHapley additive explanation (SHAP) analysis highlighted that landscape indices were key drivers in predicting SWC. These findings underscore the potential of landscape indices as valuable variables for spatial SWC prediction, supporting regional strategies for sustainable agricultural development.
The accurate prediction of the spatial variability for soil water content (SWC) in farmland is essential for water resource management and sustainable agricultural development. However, natural factors introduce uncertainty and result in poor alignment when predicting farmland SWC, leading to low accuracy. To address this, this study introduced a novel indicator: landscape indices. These indices include the largest patch index (LPI), edge density (ED), aggregation index (AI), patch cohesion index (COH), contagion index (CON), landscape division index (DIV), percentage of like adjacencies (PLA), Shannon evenness index (SHEI), and Shannon diversity index (SHDI). A Bayesian optimization–deep forest (BO–DF) model was developed to leverage these indices for predicting the spatial variability of SWC. Statistical analysis revealed that landscape indices exhibited skewed distributions and weak linear correlations with SWC (r < 0.2). Despite this, incorporating landscape index variables into the BO–DF model significantly improved prediction accuracy, with R2 increasing by 35.85%. This model demonstrated a robust nonlinear fitting capability for the spatial variability of SWC. Spatial mapping of SWC using the BO–DF model indicated that high-value areas were predominantly located in the eastern and southern regions of the Yellow River Delta in China. Furthermore, the SHapley additive explanation (SHAP) analysis highlighted that landscape indices were key drivers in predicting SWC. These findings underscore the potential of landscape indices as valuable variables for spatial SWC prediction, supporting regional strategies for sustainable agricultural development.
The effects of integrated nutrient-management (INM) practices on soil quality are essential for sustaining agro-ecosystem productivity. The soil quality index (SQI) serves as a tool to assess the physical, chemical, and biological potential of soils as influenced by various edaphic and agronomic practices. A multiyear (2018–2021) field experiment was performed at the University Organic Research Farm, Narendrapur, West Bengal, India, to investigate the influence of integrated and sole applications of different conventional fertilizers, organic (e.g., vermicompost), and natural farming inputs (e.g., Dhrava Jeevamrit and Ghana Jeevamrit) on SQIs and crop productivity of rice–mustard–green gram-based cropping systems. A total of 12 parameters were selected for the assessment of SQI, amongst which only four, namely pH, organic carbon %, total actinomycetes, and bulk density, were retained for the minimum data set based on principal component analysis (PCA). In this study, the maximum SQI value (0.901) of the experimental soil was recorded in the INM practice of 25% organic and 25% inorganic nutrient inputs, and the rest with natural farming inputs, which augments the SQI by 24% compared to the 100% inorganic nutrient treatment. Amongst the different soil parameters, the highest contribution was from the pH (35.18%), followed by organic carbon % (26.77%), total actinomycetes (10.95%), and bulk density (6.98%). The yields in different cropping systems varied year-wise across treatments. Notably, the highest yield in rainy rice was estimated in the 100% organic treatment, followed by INM practices in the subsequent years, and finally, the combination of organic and natural inputs in the final year. In the case of mustard, the combination of organic and natural inputs resulted in the highest productivity in the initial and last years of study, while the 100% organic treatment resulted in higher productivity in subsequent years. Green gram showed a dynamic shift in yield between the 100% organic and integrated treatments over the years. Further, a strong correlation was also established between the soil physico-chemical parameters and the SQI. Overall, this study concludes that the natural and organic input-based INM practice enhances the soil quality and crop productivity of the rice–mustard–green gram cropping system under the coastal saline zone.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.