Optimizing organic fertilization towards sustainable vegetable production evaluated by long-term field measurement and multi-level fuzzy comprehensive model

Agriculture Ecosystems & Environment, Journal Year: 2024, Volume and Issue: 368, P. 109008 - 109008

Published: April 3, 2024

Language: Английский

---

Comparative analysis of the effects of different dimensionality reduction algorithms on hyperspectral estimation of total nitrogen content in wheat soils

European Journal of Agronomy, Journal Year: 2025, Volume and Issue: 168, P. 127660 - 127660

Published: April 28, 2025

Language: Английский

---

Indirect Prediction Based on Machine Learning and Remote Sensing of Ecological Stoichiometric Ratio Superior to Direct Prediction

Land Degradation and Development, Journal Year: 2025, Volume and Issue: unknown

Published: May 4, 2025

ABSTRACT Exploring carbon (C), nitrogen (N), and phosphorus (P) contents as well dynamic balances in soil are important for understanding ecological characteristics stability. However, the substantial costs associated with surveys limited possibility of large‐scale surveys. The accurate predictive capability machine learning (ML) supported this possibility. In study, ML models (Random Forest, RF; support vector machine, SVM; Extreme Gradient Boosting, XGboost; Boosting Decision Tree, GBDT) remote sensing data were used to predict C, N, P stoichiometric ratio (ESR) Yellow River Delta (YRD). purpose study was assess performance four MLs predicting ESRs indirect direct predictions ESRs. results showed that RF SVM have higher accuracy than XGboost GBDT. model main factor affecting accuracy, there differences applicability different elements model. ESR prediction weaker total due fact is controlled by two elements. localized farmland wetland vegetation, substantially enhanced compared global prediction. poorer farmland. pattern reversed vegetated soil. followed calculation method improved Although not generalizable, approach still offered a multi‐element variables such Land‐use type had significant effect on mean values TC, TN, TP area 17.730 ± 2.395, 0.710 0.253, 0.691 0.089 g/kg, respectively. highest TC found vegetation soils 18.228 18.138 its old channel spatial distribution P, This clarified YRD. addition, provided an accuracy.

Language: Английский

---

General patterns of soil nutrient stoichiometry, microbial metabolic limitation and carbon use efficiency in paddy and vegetable fields along a climatic transect of eastern China

Agriculture Ecosystems & Environment, Journal Year: 2024, Volume and Issue: 378, P. 109322 - 109322

Published: Oct. 11, 2024

Language: Английский

---

Effects of fertilization on soil ecological stoichiometry and fruit quality in Karst pitaya orchard

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Aug. 7, 2024

Pitaya (Hylocereus undulatus) is a significant cash crop in the karst region of Southwest China. Ecological stoichiometry an essential method to research biogeochemical cycles and limiting elements. The purpose this study was explore stoichiometric characteristics C, N, P Karst pitaya orchards fruit quality elucidate mechanism process nutrient cycling. results showed that: (1) Fruit highest under combination chemical organic fertilizers. Compared control, contents per-fruit weight, vitamin soluble sugar increased significantly by 55.5%, 60.7%, 23.0%, respectively, while content titratable acidity decreased 22.0%. (2) soil nutrients fertilization stress downward trend general, as did microbial biomass extracellular enzyme activities. (3) Different treatments affected soil-microbial C:N ratio, C:P with areas being limited C P. (4) Spearman PLS-SEM (partial least squares-structural equation model) analysis that influence fertilization, there positive effect between microorganisms nutrients, but negative quality. offer innovative perspective on areas.

Language: Английский

---

Drivers of greenhouse gas emissions in agricultural soils: the effect of residue management and soil type

Frontiers in Environmental Science, Journal Year: 2024, Volume and Issue: 12

Published: Oct. 29, 2024

Developing successful mitigation strategies for greenhouse gases (GHGs) from crop residue returned to the soil can be difficult due an incomplete understanding of factors controlling their magnitude and direction. Therefore, this study investigates effects varying levels wheat (WR) nutrient management on GHGs emissions (CO 2 , N O, CH 4 ) across three types: Alfisol, Vertisol, Inceptisol. A combination laboratory-based measurements a variety data analysis techniques was used assess GHG responses under four WR inputs (0, 5, 10, 15 Mg/ha; WR0, WR5, WR10, WR15) (NP0: no nutrient, NP1: nutrients (N P) were added balance C/nutrient stoichiometry C/N/P= 100: 8.3: 2.0 achieve 30% stabilization C input at 5 Mg/ha (R5), NP2: 3 × NP1). The results clearly showed that averaged input, Inceptisol negative O flux, suggesting consumption which supported by its high legacy phosphorus (19.7 mg kg⁻ 1 ), elevated pH (8.49), lower clay content (13%), reduced microbial activity, as indicated biomass carbon (MBC) alkaline phosphatase (Alk-P) levels. more responsive inputs, particularly in Vertisol (15 Mg/ha) while fluxes significantly especially Alfisol exhibited highest total mineralization GWP, with cumulative GWP being 1.2 times higher than 1.4 input. partial least square (PLS) regression revealed anthropogenic influenced CO 4. drivers contributed 62% 44% variance explained responses. Our proves different biogeochemical mechanisms operate simultaneously depending influencing findings provide insight into relative contribution natural agricultural emissions, are relevant developing process-based models addressing broader challenge climate change through management.

Language: Английский

---

Explainability of Machine Learning Using Shapley Additive exPlanations (SHAP): CatBoost, XGBoost and LightGBM for Total Dissolved Gas Prediction

Studies in big data, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 25

Published: Jan. 1, 2024

Language: Английский

---

Occurrence, spatial distribution, and sources of rare earth elements in soils of large urban agglomerations in Northern China

Process Safety and Environmental Protection, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 1, 2024

Language: Английский

---