Evaluation of the Potential of Using Machine Learning and the Savitzky–Golay Filter to Estimate the Daily Soil Temperature in Gully Regions of the Chinese Loess Plateau DOI Creative Commons
Wei Deng, Dengfeng Liu,

Fengnian Guo

et al.

Agronomy, Journal Year: 2024, Volume and Issue: 14(4), P. 703 - 703

Published: March 28, 2024

Soil temperature directly affects the germination of seeds and growth crops. In order to accurately predict soil temperature, this study used RF MLP simulate shallow then with best simulation effect will be deep temperature. The models were forced by combinations environmental factors, including daily air (Tair), water vapor pressure (Pw), net radiation (Rn), moisture (VWC), which observed in Hejiashan watershed on Loess Plateau China. results showed that accuracy model for predicting proposed paper is higher than using factors testing data, range MAE was 1.158–1.610 °C, RMSE 1.449–2.088 R2 0.665–0.928, KGE 0.708–0.885 at different depths. not only provides a critical reference but also helps people better carry out agricultural production activities.

Language: Английский

Effect of Soil Moisture on Future Heatwaves Over Eastern China: Convection‐Permitting Regional Climate Simulations DOI Creative Commons

Yi Xu,

Juan Fang, Pinya Wang

et al.

Journal of Geophysical Research Atmospheres, Journal Year: 2024, Volume and Issue: 129(19)

Published: Oct. 5, 2024

Abstract Soil moisture deficiencies exacerbate heatwaves through soil moisture‐temperature feedback, an effect that is expected to intensify with climate change, resulting in critical impacts on society and ecosystems. This study aims investigate the evolving moisture‐heatwave relationship over eastern China future, using a convection‐permitting (CP, ∼4 km) regional model (RCM). The CP‐RCM simulates historical (1998–2007) future (2070–2099) climates China, three pseudo‐global warming (PGW) experiments conducted under RCP2.6, RCP4.5, RCP8.5 scenarios. Results indicate substantial increase heatwave frequency (HWF) magnitude (HWM) particularly scenario. largest HWF (up 23 days) South (SC), HWM 3.25°C) Loess Plateau (LP) North Plain (NCP), indicating pronounced risk of region. Antecedent exhibits negative correlation indices (HWM HWF) most areas suggesting its role mitigating heatwaves. Quantile regression analysis shows antecedent exerts stronger upper quantile HWF/HWM than lower quantile. With global warming, amplifying due deficiency expand spatially become more pronounced. Increased control can be attributed reduced energy limitation intensified water limitation. A comprehensive investigation across five sub‐regions reveals various regimes modulating China.

Language: Английский

Citations

1
Evaluation of the Potential of Using Machine Learning and the Savitzky–Golay Filter to Estimate the Daily Soil Temperature in Gully Regions of the Chinese Loess Plateau DOI Creative Commons
Wei Deng, Dengfeng Liu,

Fengnian Guo

et al.

Agronomy, Journal Year: 2024, Volume and Issue: 14(4), P. 703 - 703

Published: March 28, 2024

Soil temperature directly affects the germination of seeds and growth crops. In order to accurately predict soil temperature, this study used RF MLP simulate shallow then with best simulation effect will be deep temperature. The models were forced by combinations environmental factors, including daily air (Tair), water vapor pressure (Pw), net radiation (Rn), moisture (VWC), which observed in Hejiashan watershed on Loess Plateau China. results showed that accuracy model for predicting proposed paper is higher than using factors testing data, range MAE was 1.158–1.610 °C, RMSE 1.449–2.088 R2 0.665–0.928, KGE 0.708–0.885 at different depths. not only provides a critical reference but also helps people better carry out agricultural production activities.

Language: Английский

Citations

1