Skripsi
ANALISIS PENGARUH DOSIS TAWAS, PELARUTAN KAPUR, DAN DOSIS KLOR TERHADAP KESTABILAN pH AIR MENGGUNAKAN ALGORITMA MACHINE LEARNING PADA DATA OPERASIONAL PDAM
Water pH stability is a crucial parameter in drinking water treatment as it affects the quality of distributed water. This study aims to analyze the relationship between operational chemical variables and distribution water pH using a machine learning approach based on linear regression applied to PDAM operational data. The dataset includes raw water pH, alum dosage, lime dissolution per hour, chlorine dosage, and distribution water pH. The research methodology follows the CRISP-DM framework, consisting of problem understanding, data understanding, data preparation, modeling, and evaluation. The results indicate that raw water pH has a strong positive linear relationship with distribution water pH, while chemical dosage variables show relatively weak linear relationships. The linear regression model produced a coefficient of determination (R²) of 0.3665 and a Mean Absolute Error (MAE) of 0.1540, indicating moderate explanatory capability with relatively small prediction error.