Evaluating the Performance of Several Data Preprocessing Methods Based on GRU in Forecasting Monthly Runoff Time Series

Water Resources Management, Journal Year: 2024, Volume and Issue: 38(9), P. 3135 - 3152

Published: March 6, 2024

Language: Английский

---

Estimation of soil moisture in drip-irrigated citrus orchards using multi-modal UAV remote sensing

Agricultural Water Management, Journal Year: 2024, Volume and Issue: 302, P. 108972 - 108972

Published: July 30, 2024

Accurate and timely prediction of soil moisture in orchards is crucial for making informed irrigation decisions at a regional scale. Conventional methods monitoring are often limited by high cost disruption structure, etc. However, unmanned aerial vehicle (UAV) remote sensing, with spatial temporal resolutions, offers an effective alternative moisture. In this study, multi-modal UAV sensing data, including RGB, thermal infrared (TIR), multi-spectral (Mul) were acquired citrus orchards. The correlations between different sensor data analyzed to construct seven input combinations. Convolutional neural network (CNN), long short-term memory (LSTM) models new hybrid model (CNN-LSTM), employed predict depths 5 cm, 10 20 cm 40 cm. Additionally, the impact standalone sensor, texture features multi-sensor fusion on accuracy was explored. results indicated that RGB + Mul TIR achieved highest accuracy, followed those Mul, coefficient determination (R2) ranging 0.80–0.88, 0.64–0.84, 0.60–0.81, root mean square error (RMSE) 2.46–2.99 m3·m−3, 2.86–3.89 m3·m−3 3.15–4.25 respectively. Among single inputs, has 0.54–0.72, 0.36–0.52 0.14–0.26, 3.72–4.58 %, 3.81–5.04 % 4.27–6.21 CNN-LSTM exhibited CNN LSTM models, 0.20–0.88, 0.16–0.83, 0.14–0.81, 2.46–5.01 2.68–5.35 2.81–6.21 depth average 0.63, 0.62, 0.59, 0.55, 3.70 3.79 3.85 4.21 Therefore, recommended orchard. It provides method support precision decision-making.

Language: Английский

---

SMGformer: integrating STL and multi-head self-attention in deep learning model for multi-step runoff forecasting

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

Published: Oct. 9, 2024

Accurate runoff forecasting is of great significance for water resource allocation flood control and disaster reduction. However, due to the inherent strong randomness sequences, this task faces significant challenges. To address challenge, study proposes a new SMGformer forecast model. The model integrates Seasonal Trend decomposition using Loess (STL), Informer's Encoder layer, Bidirectional Gated Recurrent Unit (BiGRU), Multi-head self-attention (MHSA). Firstly, in response nonlinear non-stationary characteristics sequence, STL used extract sequence's trend, period, residual terms, multi-feature set based on 'sequence-sequence' constructed as input model, providing foundation subsequent models capture evolution runoff. key features are then captured layer. Next, BiGRU layer learn temporal information these features. further optimize output MHSA mechanism introduced emphasize impact important information. Finally, accurate achieved by transforming through Fully connected verify effectiveness proposed monthly data from two hydrological stations China selected, eight compare performance results show that compared with Informer 1th step MAE decreases 42.2% 36.6%, respectively; RMSE 37.9% 43.6% NSE increases 0.936 0.975 0.487 0.837, respectively. In addition, KGE at 3th 0.960 0.805, both which can maintain above 0.8. Therefore, accurately sequence extend effective period

Language: Английский

---

Deep learning model based on coupled SWAT and interpretable methods for water quality prediction under the influence of non-point source pollution

Computers and Electronics in Agriculture, Journal Year: 2025, Volume and Issue: 231, P. 109985 - 109985

Published: Jan. 23, 2025

Language: Английский

---

Prediction and Spatiotemporal Dynamics of Vegetation Index Based on Deep Learning and Environmental Factors in the Yangtze River Basin

Forests, Journal Year: 2025, Volume and Issue: 16(3), P. 460 - 460

Published: March 5, 2025

Accurately predicting the vegetation index (VI) of Yangtze River Basin and analyzing its spatiotemporal trends are essential for assessing dynamics providing recommendations environmental resource management in region. This study selected key climate factors most strongly correlated with three indexes (VI): Normalized Difference Vegetation Index (NDVI), Enhanced (EVI), kernel (kNDVI). Historical VI data (2001–2020) were used to train, validate, test a CNN-BiLSTM-AM deep learning model, which integrates strengths Convolutional Neural Networks (CNN), Bidirectional Long Short-Term Memory (BiLSTM), Attention Mechanism (AM). The performance this model was compared CNN-BiLSTM, LSTM, BiLSTM-AM models validate superiority VI. Finally, simulation under Shared Socioeconomic Pathway (SSP) scenarios (SSP1-1.9, SSP2-4.5, SSP5-8.5) as inputs predict next 20 years (2021–2040), aiming analyze trends. results showed following: (1) Temperature, precipitation, evapotranspiration had highest correlation time series model. (2) combined EVI achieved best (R2 = 0.981, RMSE 0.022, MAE 0.019). (3) Under all scenarios, over an upward trend previous years, significant growth observed SSP5-8.5. source region western part upper reaches increased slowly, while increases eastern reaches, middle lower estuary. analysis predicted indicates that conditions will continue improve years.

Language: Английский

---

A novel daily runoff forecasting model based on global features and enhanced local feature interpretation

Journal of Hydrology, Journal Year: 2024, Volume and Issue: unknown, P. 132227 - 132227

Published: Oct. 1, 2024

Language: Английский

---

Hypertuned wavelet convolutional neural network with long short-term memory for time series forecasting in hydroelectric power plants

Energy, Journal Year: 2024, Volume and Issue: unknown, P. 133918 - 133918

Published: Nov. 1, 2024

Language: Английский

---

Exploring Generative Adversarial Networks: Comparative Analysis of Facial Image Synthesis and the Extension of Creative Capacities in Artificial Intelligence

IEEE Access, Journal Year: 2025, Volume and Issue: 13, P. 19588 - 19597

Published: Jan. 1, 2025

Language: Английский

---

Spatiotemporal evolution of droughts and floods in the Yellow River Basin: A novel approach combining CMADS-L evaluation, hydroclimatic zonation and CNN-LSTM prediction

Journal of Hydrology Regional Studies, Journal Year: 2025, Volume and Issue: 58, P. 102250 - 102250

Published: Feb. 20, 2025

Language: Английский

---

Coupled convolutional neural network with long short-term memory network for predicting lake water temperature

Journal of Hydrology, Journal Year: 2025, Volume and Issue: unknown, P. 132878 - 132878

Published: Feb. 1, 2025

Language: Английский

---