Estimation of crop evapotranspiration using statistical and machine learning techniques with limited meteorological data: a case study in Udham Singh Nagar, India

Theoretical and Applied Climatology, Journal Year: 2024, Volume and Issue: 155(6), P. 5279 - 5296

Published: April 3, 2024

Language: Английский

---

Evaluating land use and climate change impacts on Ravi river flows using GIS and hydrological modeling approach

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

Published: Sept. 27, 2024

Language: Английский

---

An attention mechanism augmented CNN-GRU method integrating optimized variational mode decomposition and frequency feature classification for complex signal forecasting

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: unknown, P. 126464 - 126464

Published: Jan. 1, 2025

Language: Английский

---

Optimizing water management and climate-resilient agriculture in rice-fallow regions of the Dwarakeswar river basin using ML models

Deleted Journal, Journal Year: 2025, Volume and Issue: 7(4)

Published: April 11, 2025

Language: Английский

---

Improved streamflow prediction accuracy in Boreal climate watershed using a LSTM model: A comparative study

PLOS Water, Journal Year: 2025, Volume and Issue: 4(4), P. e0000359 - e0000359

Published: April 21, 2025

Streamflow plays a vital role in water resource management and environmental impact assessment. This study is novel application of the Long Short-Term Memory (LSTM) model, type recurrent neural network, for real-time streamflow prediction Upper Humber River Watershed western Newfoundland. It also compares performance LSTM model with physically based SWAT model. The was optimized by tuning hyperparameters adjusting window size to balance capturing historical data ensuring stability. Using single input variables such as daily average temperature or precipitation, achieved high Nash-Sutcliffe Efficiency (NSE) 0.95. In comparison, results show that delivers more competitive performance, achieving an NSE 0.95 versus SWAT’s 0.77, percent bias (PBIAS) 0.62 compared 8.26. Unlike SWAT, does not overestimate flows excels predicting low flows. Additionally, successfully predicted using data. Despite challenges interpretability generalizability, demonstrated strong particularly during extreme events, making it valuable tool cold climates where accurate forecasts are crucial effective management. highlights potential model’s

Language: Английский

---

Evaluating statistical and machine learning techniques for sugarcane yield forecasting in the tarai region of North India

Computers and Electronics in Agriculture, Journal Year: 2024, Volume and Issue: 229, P. 109667 - 109667

Published: Dec. 9, 2024

Language: Английский

---

Comparative evaluation of hybrid and individual models for predicting soybean yellow mosaic virus incidence

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: May 6, 2025

Abstract Forecasting the severity of crop diseases is crucial for agricultural productivity and can be achieved through statistical machine learning techniques. Predictive models that consider weather conditions during critical growth stages crops have shown promising accuracy. However, selecting most suitable forecasting model remains a challenge. This research investigates impact various factors on Soybean Yellow Mosaic Virus (SYMV) incidence. Specifically, six multivariate Stepwise Multiple Linear Regression (SMLR), Artificial Neural Networks (ANN), Least Absolute Shrinkage Selection Operator (LASSO), Ridge (RR), Elastic Net (ELNET), SMLR_ANN both direct with Principal Component Analysis (PCA)-were developed using 20 years data (2001 to 2020) predict soybean disease in Pantnagar, Uttarakhand. The dataset was divided into two parts, 80% used calibration remaining 20% validation. Model accuracy evaluated several criteria, including R², RMSE, nRMSE, MAE, PE, EF. results indicated PCA-SMLR-ANN (nRMSE val = 0.76%) effective predictor severity, closely followed by PCA-ANN 3.67%) model. Hybrid such as outperformed individual like SMLR 47.72%) ANN 6.82%). performance ranking follows: ≈ SMLR-ANN > PCA-ELNET PCA-Ridge ELNET RR PCA-LASSO LASSO PCA-SMLR SMLR. These findings highlight superior efficiency hybrid predicting based indices study region.

Language: Английский

---

Multi-time scale analysis of the water level minima in Lake Titicaca over the past 103 years

Frontiers in Climate, Journal Year: 2025, Volume and Issue: 7

Published: May 7, 2025

Lowest events in Lake Titicaca’s water level (LTWL) significantly impact local ecosystems and the drinking supply Peru Bolivia. However, hydroclimatic mechanisms driving extreme lake-level lowstands remain poorly understood. To investigate these low events, we analyzed detrended monthly LTWL anomalies, sea surface temperature (SST) datasets covering period 1921–2023. ERA5 reanalysis covers 1940–2023. A multiple linear regression model was developed to compute excluding multidecadal residual components. Interdecadal Pacific Oscillation (IPO) Decadal (PDO) indices were also for same period. Results indicate that 25% of all minima have a short duration <5 months, while remaining 75% long more than 9 respectively. All long-lived are associated with reduced moisture flow from Amazon basin toward Titicaca, but large-scale forcing varies phase change decadal component 11–15 years band PDO (PDO ). Under warm phases, driven by an enhanced South American low-level jet (SALLJ) caused SST anomalies over eastern Ocean. Warm tropical North Atlantic central cold which reinforce through reduction SALLJ. Conversely, under neutral phases westerly confined Peruvian Altiplano. Therefore, IPO do not drive because their relationship does consistent time. In conclusion, exhibit regional nature or IPO, as shows no modes

Language: Английский

---

Evaluating the Accuracy of Machine Learning, Deep Learning and Hybrid Algorithms for Flood Routing Calculations

Pure and Applied Geophysics, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 26, 2024

Language: Английский

---

Hybrid modeling approaches for agricultural commodity prices using CEEMDAN and time delay neural networks

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

Published: Nov. 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.

Language: Английский

---