Effects of alternate wetting and drying irrigation on yield, water-saving, and emission reduction in rice fields: A global meta-analysis

Agricultural and Forest Meteorology, Journal Year: 2024, Volume and Issue: 353, P. 110075 - 110075

Published: May 18, 2024

Language: Английский

---

Random kernel k-nearest neighbors regression

Frontiers in Big Data, Journal Year: 2024, Volume and Issue: 7

Published: July 1, 2024

The k-nearest neighbors (KNN) regression method, known for its nonparametric nature, is highly valued simplicity and effectiveness in handling complex structured data, particularly big data contexts. However, this method susceptible to overfitting fit discontinuity, which present significant challenges. This paper introduces the random kernel (RK-KNN) as a novel approach that well-suited applications. It integrates smoothing with bootstrap sampling enhance prediction accuracy robustness of model. aggregates multiple predictions using from training dataset selects subsets input variables KNN (K-KNN). A comprehensive evaluation RK-KNN on 15 diverse datasets, employing various functions including Gaussian Epanechnikov, demonstrates superior performance. When compared standard (R-KNN) models, it significantly reduces root mean square error (RMSE) absolute error, well improving R-squared values. variant employs specific function yielding lowest RMSE will be benchmarked against state-of-the-art methods, support vector regression, artificial neural networks, forests.

Language: Английский

---

Biochar incorporation increases grain yield, net ecosystem CO2 exchange, and decreases CH4 emissions in an alternate wetting and drying paddy ecosystem

Environmental Technology & Innovation, Journal Year: 2024, Volume and Issue: 34, P. 103577 - 103577

Published: Feb. 19, 2024

Biochar is widely used for soil carbon sequestration and improvement. However, little information available on its effects net ecosystem CO2 exchange (NEE) CH4 emissions in paddy rice systems, especially under alternate wetting drying irrigation (IAWD). A two-year field experiment was conducted with two regimes (ICF: continuous flooding irrigation; IAWD) as main plots 0 (B0) 20 t ha−1 (B1) biochar subplots. IAWD greatly decreased by 81.1-87.6% yield-scaled 81.3%-88.2% without grain yield penalty, but NEE 6.5-13.9%. The mainly caused increasing heterotrophic respiration (Rh) (Re). increased 8.1-11.3%, reduced 25.8-38.9%, 30.4-44.6% both regimes. In addition, input (gross primary product, GPP) output (Re), a higher increase GPP than Re, thus 9.7-11.1% combined can further decrease compared to biochar, achieving win-win situation of food-water-greenhouse gas trade-off, which beneficial sustainable agricultural production.

Language: Английский

---

Paddy rice methane emissions, controlling factors, and mitigation potentials across Monsoon Asia

The Science of The Total Environment, Journal Year: 2024, Volume and Issue: 935, P. 173441 - 173441

Published: May 21, 2024

Language: Английский

---

Wheat Yield Robust Prediction in the Huang-Huai-Hai Plain by Coupling Multi-Source Data with Ensemble Model under Different Irrigation and Extreme Weather Events

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(7), P. 1259 - 1259

Published: April 2, 2024

The timely and robust prediction of wheat yield is very significant for grain trade food security. In this study, the model was developed by coupling an ensemble with multi-source data, including vegetation indices (VIs) meteorological data. results showed that green chlorophyll index (GCVI) optimal remote sensing (RS) variable predicting compared other VIs. accuracy adaptive boosting- long short-term memory (AdaBoost-LSTM) higher than LSTM model. AdaBoost-LSTM coupled input data had best performance. strong robustness under different irrigation extreme weather events in general. Additionally, rainfed counties most years except years. characteristic variables window from February to April smaller requirements, which window. Therefore, can be accurately predicted one two months lead time before maturity HHHP. Overall, achieve accurate large-scale regions.

Language: Английский

---

A machine learning model using the snapshot ensemble approach for soil respiration prediction in an experimental Oak Forest

Ecological Informatics, Journal Year: 2025, Volume and Issue: 85, P. 102991 - 102991

Published: Jan. 6, 2025

Language: Английский

---

Automated Hydroponic System Measurement for Smart Greenhouses in Algeria

Solar Energy and Sustainable Development, Journal Year: 2025, Volume and Issue: 14(1), P. 111 - 130

Published: Feb. 5, 2025

Increasing food security and water shortages need creative agricultural methods, especially in dry places like Algeria. This research examines an Arduino-controlled smart greenhouse system for hydroponic barley growing, addressing the demand resource-efficient farming. The experiment at University of Tebessa (34°09'16"N, 8°07'44"E) used a semi-cylindrical (0.65m × 0.70m 0.65m) with DHT22 sensors temperature humidity monitoring, photoresistors lighting control, controlled watering systems. approach yielded 26% more (120g vs. 95g) 10 weeks instead 12 weeks. Compared to soil-based approaches, use efficiency reached 50 g/L, 70-90% decrease. Optimizing energy usage 150 kWh saved 9% over prior systems (165 kWh). To achieve 95% nutrient absorption efficiency, automated control maintained ideal growth conditions 20-25°C 60-80% relative humidity. conventional key performance indicators revealed significant improvements: average plant height grew by 18%, tiller count increased 33%, leaf area extended 1000 cm². A design spatial 20% reduced disease outbreaks 10%. These findings show that Arduino-based technology may boost production minimize resource usage, making it viable alternative sustainable agriculture locations.

Language: Английский

---

IoT-Based Smart Farming Architecture Using Federated Learning: a Nitrous Oxide Emission Prediction Use Case

ACM Journal on Computing and Sustainable Societies, Journal Year: 2025, Volume and Issue: unknown

Published: March 13, 2025

Precision agriculture and smart farming can enable real-time decision-making to optimize resources lower costs via data-driven model predictions. Adoption rates of systems are unfortunately low due farmers’ privacy concerns the high initial monetary deploying such systems. High be lowered by replacing expensive sensing equipment with machine learning models. Cloud computing used train models, but this suffers from poor privacy. Instead, fog edge local important geographical trends may lost data segmentation. Federated address these challenges. A privacy-aware Internet Things (IoT)-based architecture that uses federated was proposed. prototype deployed gather sensor a Canadian farm in Ottawa, Ontario. For various we perform nitrous oxide prediction experiments using centralized, local, federated, distributed ensemble learning. We found compete similarly well centralized Our results demonstrate our methodology potentially replace emission inexpensive sensors combined predictive analytics

Language: Английский

---

Comparing different statistical models for predicting greenhouse gas emissions, energy-, and nitrogen intensity

Computers and Electronics in Agriculture, Journal Year: 2025, Volume and Issue: 234, P. 110209 - 110209

Published: March 18, 2025

Language: Английский

---

Quantitative assessment and mitigation strategies of greenhouse gas emissions from rice fields in China: A data-driven approach based on machine learning and statistical modeling

Computers and Electronics in Agriculture, Journal Year: 2023, Volume and Issue: 210, P. 107929 - 107929

Published: May 21, 2023

Language: Английский

---