CD Tesis

Penerapan Model Berbasis Artificial Neural Network Untuk Memprediksi Kualitas Air Di Sungai Subayang Kabupaten Kampar

---

The life of the Indonesian people cannot be separated from the river, because the river is one of the sources of livelihood, ranging from agriculture to trade and is the most widely used as meeting household needs for most people in Indonesia. The Subayang River is one of the rivers in the Kampar Regency and is a sub-watershed of the Kampar Kiri River. Administratively, the Subayang River is included in the Bukit Rimbang Bukit Baling Wildlife Sanctuary. The length of the Subayang River reaching 90 km has various benefits for the community, from economic functions, transportation, socio-culture and for bathing, washing also toilet facilities. As a water transportation route, the Subayang Sub-watershed is an important route for the community to access between villages located along the river. Community activities that mostly utilize the Subayang River will certainly have an impact on the biota and quality of the river (Syuhada et al, 2017).
Degradation and declining quality of the environmental carrying capacity can change the structure and function of the existing community, and the changes that occur depend on the tolerance capability of each constituent species. Each species of organism has a different tolerance threshold for contamination and will have consequences in the ability of species to compete in environment. Illegal logging and land use change also increase to the problem for the Subayang River which causes a decrease in river quality.
Water quality management is very important to do, because water is an inseparable part of everyday human life. Monitoring water quality is a way to maintain the quality of water, especially the river. Monitoring the quality of the river that we are doing today requires a lot of equipment, effort and expertise so that to implement it becomes expensive and complicated. Currently the technology is growing rapidly by using artificial intelligence as the backbone of the Industrial Revolution 4.0 which promises a lot of convenience for industry and government. One of artificial intelligence technology is machine learning with Artificial Neural Network (ANN) algorithm which is commonly used to predict or estimate a future value. This artificial neural network can be used to help monitor river water quality.
The objective of this research to develop Artificial Neural Networks (ANN) model to predict the paramater of river quality (DO, pH, turbidity, temperature, water flow, conductivity) in the Subayang River, Kampar Regency, using software Rapidminer. The performance of the ANN models was evaluated using root mean squared error (RMSE) and correlation squared (R2) as a second comparison, then the results of the testing implementation are compared with direct measurements in the field. With the RMSE values obtained in the test results of each parameter DO = 1.613, pH = 0.098, turbidity = 4.730, temperature = 0.493, water flow = 0.121 and conductivity = 0.909. The lower the RMSE level, the closer it is to Artificial Neural Network accuracy for value prediction. Based on direct measurements in the Subayang River and calculations using modeling with an Artificial Neural Network algorithm the results when referring to the quality standard PP No. 82 of 2001 regarding water quality management and water pollution control, that this value is still below the quality standard threshold, still within normal category.
Determination of water quality status using the pollution index method based on Kepmen LH No. 115 of 2003, research data for the pollution index uses direct measurements with Neural Network modeling, the results obtained are still in the category of good (not polluted), up to lightly polluted.
Most of the people who live around the Subayang River are quite positive by always regulating clean lifestyle, but there are only a few that apply it in daily life, for example there are still many people who throw garbage out of place, as well as MCK activities, which are still carried out in the river with reasons for the availability of facilities that are still lacking and also because it has become a habit, as well as the lack of public awareness of the need to protect the environment due to illegal logging and mining activities, and indirectly affect to the results of water quality predictions, in this case the results of turbidity predictions for ANN based modeling of Subayang River waters.

Key Words: Artificial Neural Network, water quality prediction, Subayang River

---

Ketersediaan

Informasi Detail

Judul Seri

-

No. Panggil

10 01. 220 (0010)

Penerbit

Pekanbaru : Universitas Riau – Pascasarjana – Tesis Ilmu Lingkungan., 2020

Deskripsi Fisik

xii, 120 hlm.; ill.; 29 cm

Bahasa

Indonesia

ISBN/ISSN

-

Klasifikasi

10 01. 220 (0010)

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

PASCASARJANA (MAGISTER) ILMU LINGKUNGAN

Info Detail Spesifik

-

Pernyataan Tanggungjawab

FATAH

Versi lain/terkait

Lampiran Berkas

Komentar

---

Anda harus masuk sebelum memberikan komentar