IPB University Logo

SCIENTIFIC REPOSITORY

IPB University Scientific Repository collects, disseminates, and provides persistent and reliable access to the research and scholarship of faculty, staff, and students at IPB University

AI Repository
 
Building and Categories


      View Item 
      •   IPB Repository
      • Final Assignments
      • Undergraduate Final Assignments
      • UF - School of Data Science, Mathematic and Informatics
      • UF - Computer Science
      • View Item
      •   IPB Repository
      • Final Assignments
      • Undergraduate Final Assignments
      • UF - School of Data Science, Mathematic and Informatics
      • UF - Computer Science
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Pembangunan Model Prediksi Kualitas Air pada Rainwater Harvesting System Berbasis Machine Learning

      Thumbnail
      View/Open
      Cover (478.8Kb)
      Fulltext (1.737Mb)
      Lampiran (218.0Kb)
      Date
      2026
      Jenis/Type
      Skripsi
      Subtype
      Undergraduate Theses
      Author
      WINARNO, VIBY LADYSCHA YALASENA
      Hardhienata, Medria Kusuma Dewi
      Kusuma, Wisnu Ananta
      Metadata
      Show full item record
      Abstract
      Air bersih merupakan kebutuhan dasar manusia, namun ketersediaannya di Indonesia, khususnya di beberapa wilayah Pulau Jawa dan Bali masih terbatas terutama pada saat terjadi musim kemarau panjang. Rainwater Harvesting System (RHS) dapat menjadi solusi alternatif dalam mendukung pemenuhan kebutuhan air secara berkelanjutan, meskipun masih menghadapi kendala pada kualitas air hasil tampungan. Penelitian ini bertujuan untuk membangun model prediksi kualitas air pada RHS dengan mempertimbangkan parameter pH dan tingkat kekeruhan air menggunakan algoritma machine learning. Algoritma yang diuji dalam penelitian ini adalah algoritma Logistic Regression, K-Nearest Neighbors, Support Vector Machine, Decision Tree, Random Forest, dan XGBoost. Tahapan penelitian meliputi pengumpulan dan praproses data, pelabelan data dengan metode Weighted Arithmetic Water Quality Index (WAWQI), pembagian data, penanganan ketidakseimbangan data dengan SMOTE, serta pembangunan model prediksi dan evaluasi model. Berdasarkan evaluasi kinerja model, XGBoost memberikan hasil terbaik dengan nilai accuracy sebesar 99,66%, precision 98,75%, recall 98,26%, dan F1-score sebesar 98,50% yang menunjukkan tingkat kinerja yang tinggi. Hasil penelitian ini menunjukkan potensi penggunaan machine learning untuk memprediksi kualitas air pada RHS. Selain itu, penelitian ini juga menguji perbandingan penggunaan parameter pH, tingkat kekeruhan, suhu, dan Total Dissolved Solids (TDS). Hasil penelitian menunjukkan bahwa model dengan keterbatasan parameter tetap mampu memberikan kinerja yang baik dalam memprediksi kualitas air.
       
      Clean water is a basic human need, but its availability in Indonesia, especially in some areas of Java and Bali is still limited during the long dry season. The Rainwater Harvesting System (RHS) can be an alternative solution in supporting the fulfillment of water needs in a sustainable manner, although it still faces obstacles to the quality of water from the reservoir. This study aims to build a water quality prediction model in RHS by considering pH parameters and turbidity levels using machine learning algorithms. The algorithms tested in this study are the Logistic Regression, K-Nearest Neighbors, Support Vector Machine, Decision Tree, Random Forest, and XGBoost algorithms. The research stages include data collection and preprocessing, data labeling using the Weighted Arithmetic Water Quality Index (WAWQI) method, data splitting, handling data imbalances with SMOTE, and model prediction and evaluation development. Based on the model performance evaluation, XGBoost gave the best results with an accuracy value of 99.66%, precision of 98.75%, recall of 98.26%, and an F1-score of 98.50% indicating a high level of performance. The results of this study show the potential use of machine learning to predict water quality in RHS. In addition, this study also tested the comparison of the use of pH, turbidity levels, temperature, and Total Dissolved Solids (TDS) parameters. The results show that models with limited parameters are able to provide good performance in predicting water quality.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/177038
      Collections
      • UF - Computer Science [164]

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository
        

       

      Browse

      All of IPB RepositoryCollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

      My Account

      Login

      Application

      google store

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository