Generalized Multiprocess Kbest-Based Expert System for Improved Multitemporal Evapotranspiration Forecasting in California, United States DOI
Jinwook Lee, Sayed M. Bateni, Changhyun Jun

и другие.

Опубликована: Янв. 1, 2023

Evapotranspiration is an essential component of the hydrological cycle. Forecasting reference crop evapotranspiration (ETo) using a reliable and generalized framework crucial for agricultural operations, especially irrigation. This study was aimed at evaluating performance multivariate-multitemporal intelligent system including K-Best selection (KBest), multivariate variational mode decomposition (MVMD), cascade forward neural network (CFNN) 1-, 3-, 7-, 10-day-ahead forecasting daily ETo in twelve stations California, one significant regions U.S. The input variables included solar radiation, maximum temperature, minimum average dew point, vapor pressure, relative humidity. analysis covered span 20 years, from 2003 to 2022. In additional CFNN, two other machine learning models, namely, extreme (ELM) bagging regression tree (BRT), were integrated with various preprocessing techniques construct three hybrid i.e., MVMD-KBest-CFNN, MVMD-KBest-ELM, MVMD-KBest-BRT. Using MVMD technique, antecedent information features factorized into intrinsic functions residuals. Subsequently, most influential sub-components filtered KBest reduce computational cost enhance accuracy before inputting models. Several statistical indices, such as correlation coefficient (R) root mean square error (RMSE), used addition diagnostic validation methods assess robustness frameworks standalone According results obtained testing phase, averaged across all stations, MVMD-KBest-CFNN MVMD-KBest-ELM models outperformed MVMD-KBest-BRT model, R values 0.983, 0.980, 0.977, 0.968 forecasts, respectively. corresponding RMSE 0.390, 0.416, 0.450, 0.517 mm/d, demonstrating commendable prediction even longer lead times.

Язык: Английский

Better with fewer features: climate dynamics estimation for Van Lake basin using feature selection DOI
Önder Çoban, Musa Eşit, Sercan Yalçın

и другие.

Environmental Science and Pollution Research, Год журнала: 2025, Номер unknown

Опубликована: Фев. 17, 2025

Язык: Английский

Процитировано

0
Integrative Approaches to Soybean Resilience, Productivity, and Utility: A Review of Genomics, Computational Modeling, and Economic Viability DOI Creative Commons

Yu-Hong Gai,

Shu-Hao Liu,

Zhidan Zhang

и другие.

Plants, Год журнала: 2025, Номер 14(5), С. 671 - 671

Опубликована: Фев. 21, 2025

Soybean is a vital crop globally and key source of food, feed, biofuel. With advancements in high-throughput technologies, soybeans have become target for genetic improvement. This comprehensive review explores advances multi-omics, artificial intelligence, economic sustainability to enhance soybean resilience productivity. Genomics revolution, including marker-assisted selection (MAS), genomic (GS), genome-wide association studies (GWAS), QTL mapping, GBS, CRISPR-Cas9, metagenomics, metabolomics boosted the growth development by creating stress-resilient varieties. The intelligence (AI) machine learning approaches are improving trait discovery associated with nutritional quality, stresses, adaptation soybeans. Additionally, AI-driven technologies like IoT-based disease detection deep revolutionizing monitoring, early identification, yield prediction, prevention, precision farming. viability environmental soybean-derived biofuels critically evaluated, focusing on trade-offs policy implications. Finally, potential impact climate change productivity explored through predictive modeling adaptive strategies. Thus, this study highlights transformative multidisciplinary advancing global utility.

Язык: Английский

Процитировано

0
Estimating Daily Reference Crop Evapotranspiration in Northeast China Using Optimized Empirical Models Based on Heuristic Intelligence Algorithms DOI Creative Commons
Zongyang Li, Zhongkuo Zhao, Liwen Xing

и другие.

Agronomy, Год журнала: 2025, Номер 15(3), С. 599 - 599

Опубликована: Фев. 27, 2025

Accurately estimating reference crop evapotranspiration (ETo) improves agricultural water use efficiency. However, the accuracy of ETo estimation needs to be further improved in Northeast region China, country’s main grain production area. In this research, meteorological data from 30 sites China over past 59 years (1961–2019) were selected evaluate simulation 11 models. By using least square method (LSM) and three population heuristic intelligent algorithms—a genetic algorithm (GA), a particle swarm optimization (PSO), differential evolution (DE)—the parameters eleven kinds models optimized, respectively, model suitable for northeast was selected. The results showed that radiation-based Jensen Haise (JH) had best among empirical models, with R2 0.92. Hamon an acceptable accuracy, while combination low ranges 0.74–0.88. After LSM optimization, all been significantly by 0.58–12.1%. algorithms Door optimized GA DE higher Although JH requires more factors than model, it shows better stability. Regardless original formula or various algorithms, has is greater 0.91. Therefore, when only temperature radiation available, recommended estimate ETo, respectively; both underestimated absolute error range 0.01–0.02 mm d−1 compared Penman–Monteith (P–M) equation. When could used less 0.01 d−1. This study provided accurate within regional scope incomplete data.

Язык: Английский

Процитировано

0
Evapotranspiration Prediction Method Based on K-Means Clustering and QPSO-MKELM Model DOI Creative Commons

Chuansheng Zhang,

Minglai Yang

Applied Sciences, Год журнала: 2025, Номер 15(7), С. 3530 - 3530

Опубликована: Март 24, 2025

This study aims to improve the prediction accuracy of reference evapotranspiration under limited meteorological factors. Based on commonly recommended PSO-ELM model for ET0 and addressing its limitations, an improved QPSO algorithm multiple kernel functions are introduced. Additionally, a novel model, Kmeans-QPSO-MKELM, is proposed, incorporating K-means clustering estimate daily in Yancheng, Jiangsu Province, China. In input selection process, based variance correlation coefficients various factors, eight models attempting incorporate sine cosine values date. The new then subjected ablation comparison experiments. Ablation experiment results show that introducing improves model’s running speed, while introduction enhance accuracy. improvement brought by was especially significant when wind speed included. Comparison indicate significantly higher than all other models, after including date input. only slower RF model. Therefore, Kmeans-QPSO-MKELM using as inputs, provides fast accurate approach predicting evapotranspiration.

Язык: Английский

Процитировано

0
Sequence-to-sequence and meta LSTM techniques enhanced by remote sensing for advanced evapotranspiration estimation DOI

Sajjad Hashemi,

Saeed Samadianfard,

Amir Hossein Nazemi

и другие.

Earth Science Informatics, Год журнала: 2025, Номер 18(2)

Опубликована: Май 1, 2025

Процитировано

0
Estimation of daily reference crop evapotranspiration in China based on time-space-LSTM model DOI

Zhenyuan Sun,

Boyan Sun, Shuang Li

и другие.

Journal of Hydrology, Год журнала: 2025, Номер unknown, С. 133430 - 133430

Опубликована: Май 1, 2025

Язык: Английский

Процитировано

0
Egypt's water future: AI predicts evapotranspiration shifts across climate zones DOI Creative Commons
Ali Mokhtar, Mohammed Magdy Hamed, Hongming He

и другие.

Journal of Hydrology Regional Studies, Год журнала: 2024, Номер 56, С. 101968 - 101968

Опубликована: Сен. 17, 2024

Язык: Английский

Процитировано

2
A Novel Hybrid Deep Learning Framework for Evaluating Field Evapotranspiration Considering the Impact of Soil Salinity DOI Creative Commons
Yao Rong, Weishu Wang,

Peijin Wu

и другие.

Water Resources Research, Год журнала: 2024, Номер 60(9)

Опубликована: Сен. 1, 2024

Abstract Accurate evaluation of evapotranspiration ( ET ) is crucial for efficient agricultural water management. Data‐driven models exhibit strong predictive capabilities, yet significant limitations like naive extrapolation hamper wider generalization. In this perspective, we explore a novel hybrid deep learning DL framework to integrate domain knowledge and demonstrate its potential evaluating under the influence soil salinity. Specifically, integrated physical constraints from process (Penman‐Monteith or Shuttleworth‐Wallace) salinity‐induced stomatal stress mechanisms into algorithm, evaluated performance by comparing four diverse scenarios. Results that offers promising alternative estimation, achieving comparable accuracy pure during training validation. Nonetheless, due limited available measurements, data‐driven model may not adequately capture plant responses salt stress, leading prediction biases observed independent testing. Encouragingly, DL‐SS integrating Shuttleworth‐Wallace demonstrated enhanced interpretability, generalizability, capabilities. During testing, consistently showed optimal performance, yielding root mean square error RMSE values 37.4 W m −2 sunflower 39.2 maize. Compared traditional Jarvis‐type approaches JPM JSW achieved substantial reductions in values: 51%, 33%, 43% sunflower, 45%, 31%, 35% maize, respectively. These findings highlight importance prior scientific enhance capability modeling, especially salinized regions where conventional struggle.

Язык: Английский

Процитировано

1
Generalized Multiprocess Kbest-Based Expert System for Improved Multitemporal Evapotranspiration Forecasting in California, United States DOI
Jinwook Lee, Sayed M. Bateni, Changhyun Jun

и другие.

Опубликована: Янв. 1, 2023

Evapotranspiration is an essential component of the hydrological cycle. Forecasting reference crop evapotranspiration (ETo) using a reliable and generalized framework crucial for agricultural operations, especially irrigation. This study was aimed at evaluating performance multivariate-multitemporal intelligent system including K-Best selection (KBest), multivariate variational mode decomposition (MVMD), cascade forward neural network (CFNN) 1-, 3-, 7-, 10-day-ahead forecasting daily ETo in twelve stations California, one significant regions U.S. The input variables included solar radiation, maximum temperature, minimum average dew point, vapor pressure, relative humidity. analysis covered span 20 years, from 2003 to 2022. In additional CFNN, two other machine learning models, namely, extreme (ELM) bagging regression tree (BRT), were integrated with various preprocessing techniques construct three hybrid i.e., MVMD-KBest-CFNN, MVMD-KBest-ELM, MVMD-KBest-BRT. Using MVMD technique, antecedent information features factorized into intrinsic functions residuals. Subsequently, most influential sub-components filtered KBest reduce computational cost enhance accuracy before inputting models. Several statistical indices, such as correlation coefficient (R) root mean square error (RMSE), used addition diagnostic validation methods assess robustness frameworks standalone According results obtained testing phase, averaged across all stations, MVMD-KBest-CFNN MVMD-KBest-ELM models outperformed MVMD-KBest-BRT model, R values 0.983, 0.980, 0.977, 0.968 forecasts, respectively. corresponding RMSE 0.390, 0.416, 0.450, 0.517 mm/d, demonstrating commendable prediction even longer lead times.

Язык: Английский

Процитировано

0