Environmental and Ecological Statistics, Год журнала: 2024, Номер unknown
Опубликована: Июль 23, 2024
Язык: Английский
Environmental and Ecological Statistics, Год журнала: 2024, Номер unknown
Опубликована: Июль 23, 2024
Язык: Английский
Scientific Reports, Год журнала: 2025, Номер 15(1)
Опубликована: Янв. 20, 2025
Язык: Английский
Процитировано
5Earth Systems and Environment, Год журнала: 2025, Номер unknown
Опубликована: Янв. 2, 2025
Язык: Английский
Процитировано
2Water, Год журнала: 2025, Номер 17(9), С. 1304 - 1304
Опубликована: Апрель 27, 2025
The present investigation utilized artificial neural networks (ANN) and gene expression programming (GEP) in comparison with the two-point method (TPM) to develop a generalized solution for predicting infiltrated water volume (∀Z) across various soil types under furrow conditions. This work assesses infiltration behavior respect experimental data from several temporal contexts. Data distribution model performance are evaluated via descriptive statistics correlation tests. Artificial intelligence (AI) models (ANN GEP) trained utilizing input variables—inflow rate (Qin); length (L); waterfront advance time at end of (TL); opportunity (To); cross-sectional area inflow (Ao) compared TPM performance. More precisely consistently than power function, AI-based algorithms hope be invading volume. Statistical analysis shows that ANN GEP have lower error metrics, increased generalizability, better representation complex dynamics. determination coefficient (R2) produced 98.1% testing 97.8% validation, while showed accuracy reductions 2.5% 4.6%, respectively. On other side, R2 95.7% 96.1% 0.7% 3%, During computation, TPMs root mean square (RMSE) 0.0135 m3/m exceeded all values. Errors within 10% relative deviation were displayed using ∀Z. Particularly, GEP, study revealed AI techniques predict irrigation penetration function. These adaptation, extrapolation, accuracy. Results show AI-driven modeling may maximize hydrological assessments control.
Язык: Английский
Процитировано
1European Journal of Agronomy, Год журнала: 2024, Номер 160, С. 127297 - 127297
Опубликована: Авг. 10, 2024
Язык: Английский
Процитировано
6Scientific Reports, Год журнала: 2024, Номер 14(1)
Опубликована: Сен. 27, 2024
Язык: Английский
Процитировано
4Computers and Electronics in Agriculture, Год журнала: 2024, Номер 229, С. 109667 - 109667
Опубликована: Дек. 9, 2024
Язык: Английский
Процитировано
3Physics and Chemistry of the Earth Parts A/B/C, Год журнала: 2025, Номер unknown, С. 103879 - 103879
Опубликована: Янв. 1, 2025
Язык: Английский
Процитировано
0Water, Год журнала: 2025, Номер 17(9), С. 1384 - 1384
Опубликована: Май 4, 2025
Evapotranspiration (ET) has a significant role in various natural and human systems, such as water cycle balance, climate regulation, ecosystem health, agriculture, hydrological cycle, resource management, studies. Among approaches that are employed for estimating ET, the Penman–Monteith equation is known widely accepted reference approach. However, extensive data requirement of this method crucial challenge limits its usage, particularly data-scarce regions. Therefore, an alternative approach, artificial intelligence (AI) models have gained prominence evapotranspiration because their capacity to handle complicated relationships between meteorological variables loss processes. These leverage large datasets advanced algorithms provide accurate timely ET predictions. The current research aims review previous studies addressing application AI model modeling under four main categories: neuron-based, tree-based, kernel-based, hybrid models. results study indicated traditional like (PM) require input data, while AI-based offer promising alternatives due ability complex nonlinear relationships. Despite potential, face challenges overfitting, interpretability, inconsistent variable selection, lack integration with physical processes, highlighting need standardized configurations, better pre-processing techniques, incorporation remote sensing data.
Язык: Английский
Процитировано
0Scientific Reports, Год журнала: 2024, Номер 14(1)
Опубликована: Ноя. 4, 2024
Abstract Improving the forecasting accuracy of agricultural commodity prices is critical for many stakeholders namely, farmers, traders, exporters, governments, and all other partners in price channel, to evade risks enable appropriate policy interventions. However, traditional mono-scale smoothing techniques often fail capture non-stationary non-linear features due their multifarious structure. This study has proposed a CEEMDAN (Complete Ensemble Empirical Mode Decomposition with Adaptive Noise)-TDNN (Time Delay Neural Network) model non-linear, series. evaluated its suitability comparison three major EMD (Empirical Decomposition) variants (EMD, Complementary EMD) benchmark (Autoregressive Integrated Moving Average, Non-linear Support Vector Regression, Gradient Boosting Machine, Random Forest TDNN) models using monthly wholesale oilseed crops India. Outcomes from this investigation reflect that CEEMDAN-TDNN hybrid have outperformed on basis evaluation metrics under consideration. For model, an average improvement RMSE (Root Mean Square Error), Relative MAPE (Mean Absolute Percentage Error) values been observed be 20.04%, 19.94% 27.80%, respectively over variant-based counterparts 57.66%, 48.37% 62.37%, stochastic machine learning models. The CEEMD-TDNN demonstrated superior performance predicting directional changes series compared Additionally, forecasts generated by assessed Diebold-Mariano test, Friedman Taylor diagram. results confirm alternative models, providing distinct advantage.
Язык: Английский
Процитировано
2Environmental and Ecological Statistics, Год журнала: 2024, Номер unknown
Опубликована: Июль 23, 2024
Язык: Английский
Процитировано
0