Selecting a Time-Series Model to Predict Drinking Water Extraction in a Semi-Arid Region in Chihuahua, Mexico DOI Open Access
Martín Alfredo Legarreta-González, César A. Meza‐Herrera, Rafael Rodríguez-Martínez

et al.

Sustainability, Journal Year: 2024, Volume and Issue: 16(22), P. 9722 - 9722

Published: Nov. 7, 2024

As the effects of global climate change intensify, it is increasingly important to implement more effective water management practices, particularly in arid and semi-arid regions such as Meoqui, Chihuahua, situated northern center Mexico. The objective this study was identify optimal time-series model for analyzing pattern extraction volumes predicting a one-year forecast. It hypothesized that volume extracted over time could be explained by statistical model, with future trends. To achieve objective, three models were evaluated. assess groundwater extraction, employed: seasonal autoregressive integrated moving average (SARIMA), Prophet, Prophet extreme gradient boosting (XGBoost). mean entire period 50,935 ± 47,540 m3, total 67,233,578 m3 from all wells. greatest has historically been urban wells, an 55,720 48,865 63,520,284 m3. raw wells determined 20,629 19,767 3,713,294 SARIMA(1,1,1)(1,0,0)12 identified general while “white noise” ARIMA(0,1,0) water, SARIMA(2,1,1)(2,0,0)12 These findings serve reinforce efficacy SARIMA forecasting provide basis resource managers region develop policies promote sustainable management.

Language: Английский

Selecting a Time-Series Model to Predict Drinking Water Extraction in a Semi-Arid Region in Chihuahua, Mexico DOI Open Access
Martín Alfredo Legarreta-González, César A. Meza‐Herrera, Rafael Rodríguez-Martínez

et al.

Sustainability, Journal Year: 2024, Volume and Issue: 16(22), P. 9722 - 9722

Published: Nov. 7, 2024

As the effects of global climate change intensify, it is increasingly important to implement more effective water management practices, particularly in arid and semi-arid regions such as Meoqui, Chihuahua, situated northern center Mexico. The objective this study was identify optimal time-series model for analyzing pattern extraction volumes predicting a one-year forecast. It hypothesized that volume extracted over time could be explained by statistical model, with future trends. To achieve objective, three models were evaluated. assess groundwater extraction, employed: seasonal autoregressive integrated moving average (SARIMA), Prophet, Prophet extreme gradient boosting (XGBoost). mean entire period 50,935 ± 47,540 m3, total 67,233,578 m3 from all wells. greatest has historically been urban wells, an 55,720 48,865 63,520,284 m3. raw wells determined 20,629 19,767 3,713,294 SARIMA(1,1,1)(1,0,0)12 identified general while “white noise” ARIMA(0,1,0) water, SARIMA(2,1,1)(2,0,0)12 These findings serve reinforce efficacy SARIMA forecasting provide basis resource managers region develop policies promote sustainable management.

Language: Английский

Citations

1