Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Recurso digital |
| Lingua: | inglese |
| Pubblicazione: |
Zenodo
2026
|
| Accesso online: | https://doi.org/10.5281/zenodo.20285301 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866901507333423104 |
|---|---|
| author | Chinmay Kulkarni, Chinmay Kulkarni Shivtej Sul, Shivtej Sul Samadhan Lade, Samadhan Lade Kartik Patil, Kartik Patil ADCET |
| author_facet | Chinmay Kulkarni, Chinmay Kulkarni Shivtej Sul, Shivtej Sul Samadhan Lade, Samadhan Lade Kartik Patil, Kartik Patil ADCET |
| contents | <p>—The degradation of global water quality,<br>driven by rapid industrialization and urbanization,<br>poses a severe threat to public health. Traditional<br>monitoring methods are often slow and labor-intensive,<br>struggling to handle the non-linear, high-volume data<br>from modern sensor networks. This paper presents an<br>intelligent "Water Analysis and Predictions System"<br>that leverages Machine Learning (ML) to provide<br>accurate water quality assessment. By processing<br>physico-chemical parameters such as pH, Dissolved<br>Oxygen, and Turbidity, we trained models including<br>Random Forest, SVM, and Gradient Boosting<br>(XGBoost). Our results indicate that ensemble methods<br>achieve superior accuracy (up to 97.2%) in classifying<br>potability and predicting the Water Quality Index<br>(WQI). This data-driven framework offers a proactive<br>solution for environmental resource management</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_20285301 |
| institution | Zenodo |
| language | eng |
| publishDate | 2026 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Water Analysis And Prediction ADCET26 Chinmay Kulkarni, Chinmay Kulkarni Shivtej Sul, Shivtej Sul Samadhan Lade, Samadhan Lade Kartik Patil, Kartik Patil ADCET <p>—The degradation of global water quality,<br>driven by rapid industrialization and urbanization,<br>poses a severe threat to public health. Traditional<br>monitoring methods are often slow and labor-intensive,<br>struggling to handle the non-linear, high-volume data<br>from modern sensor networks. This paper presents an<br>intelligent "Water Analysis and Predictions System"<br>that leverages Machine Learning (ML) to provide<br>accurate water quality assessment. By processing<br>physico-chemical parameters such as pH, Dissolved<br>Oxygen, and Turbidity, we trained models including<br>Random Forest, SVM, and Gradient Boosting<br>(XGBoost). Our results indicate that ensemble methods<br>achieve superior accuracy (up to 97.2%) in classifying<br>potability and predicting the Water Quality Index<br>(WQI). This data-driven framework offers a proactive<br>solution for environmental resource management</p> |
| title | Water Analysis And Prediction ADCET26 |
| url | https://doi.org/10.5281/zenodo.20285301 |