Prediction Model of Farmland Water Conservancy Project Cost Index Based on PCA–DBO–SVR DOI Open Access

X.-Rong Li,

Kun Yeun Han, Wenhe Liu

et al.

Sustainability, Journal Year: 2025, Volume and Issue: 17(6), P. 2702 - 2702

Published: March 18, 2025

With the gradual cessation of budget quota standards and emphasis on market-based pricing, accurately predicting project investments has become a critical issue in construction management. This study focuses cost indicator prediction for irrigation drainage projects to address absence farmland water conservancy achieve accurate efficient investment prediction. Engineering characteristics affecting indicators were comprehensively analyzed, principal component analysis (PCA) was employed identify key influencing factors. A model proposed based support vector regression (SVR) optimized using dung beetle optimizer (DBO) algorithm. The DBO algorithm SVR hyperparameters, resolving issues poor generalization long times. Validation 2024 data from Liaoning Province showed that PCA–DBO–SVR achieved superior performance. For electromechanical well projects, root mean square error (RMSE) 1.116 million CNY, absolute (MAE) 0.910 percentage (MAPE) 3.261%, R2 reached 0.962. ditch 0.500 MAE 0.281 MAPE 3.732%, 0.923. outperformed BP, SVR, PCA–SVR models all evaluations, demonstrating higher accuracy better capability. provides theoretical developing offers valuable insights dynamically adjusting national improving fund

Language: Английский

Prediction Model of Farmland Water Conservancy Project Cost Index Based on PCA–DBO–SVR DOI Open Access

X.-Rong Li,

Kun Yeun Han, Wenhe Liu

et al.

Sustainability, Journal Year: 2025, Volume and Issue: 17(6), P. 2702 - 2702

Published: March 18, 2025

With the gradual cessation of budget quota standards and emphasis on market-based pricing, accurately predicting project investments has become a critical issue in construction management. This study focuses cost indicator prediction for irrigation drainage projects to address absence farmland water conservancy achieve accurate efficient investment prediction. Engineering characteristics affecting indicators were comprehensively analyzed, principal component analysis (PCA) was employed identify key influencing factors. A model proposed based support vector regression (SVR) optimized using dung beetle optimizer (DBO) algorithm. The DBO algorithm SVR hyperparameters, resolving issues poor generalization long times. Validation 2024 data from Liaoning Province showed that PCA–DBO–SVR achieved superior performance. For electromechanical well projects, root mean square error (RMSE) 1.116 million CNY, absolute (MAE) 0.910 percentage (MAPE) 3.261%, R2 reached 0.962. ditch 0.500 MAE 0.281 MAPE 3.732%, 0.923. outperformed BP, SVR, PCA–SVR models all evaluations, demonstrating higher accuracy better capability. provides theoretical developing offers valuable insights dynamically adjusting national improving fund

Language: Английский

Citations

0