Modeling Discharge and Water Chemistry Using Artificial Neural Network
| Main Author: | |
|---|---|
| Language: | English |
| Published: |
Ohio University / OhioLINK
2021
|
| Subjects: | |
| Online Access: | http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1620167556121952 |
| id |
ndltd-OhioLink-oai-etd.ohiolink.edu-ohiou1620167556121952 |
|---|---|
| record_format |
oai_dc |
| spelling |
ndltd-OhioLink-oai-etd.ohiolink.edu-ohiou16201675561219522021-09-11T05:17:14Z Modeling Discharge and Water Chemistry Using Artificial Neural Network Ajayi, Toluwaleke Geology Artificial Neural Network discharge acid mine drainage precipitation evapotranspiration climate change In southeast Ohio, Raccoon Creek Watershed (RC) has an extensive mining history resulting in acid mine drainage (AMD) and subsequent environmental problems. Modeling of the discharge and chemistry, as well as an assessment of the impact of climate change in discharge and chemistry of AMD, impacted Hewett Fork, a tributary of Raccoon Creek, is the focus of this thesis. Discharge measurements are collected by the United States Geological Survey (USGS) gage station at the Bolin Mills (BM) station on the main stem of Raccoon Creek. This data for the period 2011-2019 has been analyzed to develop a prediction model for BM discharge, in addition to assessing the impact of climate change on BM flow event under two climate scenario (RCP4.5 and RCP 8.5) and subsequently use the model to predict flow and water chemistry in Hewett Fork. Precipitation, antecedent precipitation index (API), and air temperature were the input variables considered in this study for transient data analysis using the program PAST, and additional variable such as antecedent temperature index (ATI), and potential evapotranspiration (ET) for modeling studies using Artificial Neural Networks (program NeuroShell2). The result of the transient data analysis highlighted the quick flow, baseflow of the watershed, delay time, and total response time. The immediate response time (zero-day lag) of BM discharge following API, in addition to its strong spectrum signal (0.22Hz), indicates a strong influence of API on BM discharge. The Neural Network Model using group method of data handling (GMDH) and generalized regression neural network (GRNN) shows a variation of prediction models for BM due to parameters such as decay factor in API and ATI, as well as in the evapotranspiration input variables of the model. However, the study reveals that the GRNN model for BM is the most suitable for BM prediction based on its performance, with an r-value greater than 0.90, and its ease in predicting discharge by specifying a data set to be added to the data set for training and calibrating the network. The result of the water chemistry model using GMDH, with r values greater than 0.80 for each model, shows the input variables have a good capacity to predict chemical concentration/load in the HF stream. Five climate model projections for the future periods 2020-2039, 2040-2059, 2060-2079, and 2080-2099 were analyzed in this study to simulate three flow events(high, low, and intermediate flow) in BM. The flows simulated by the GRNN model in response to the future climate model projections showed a consistent increase in low flow and high flow and a decrease in intermediate flow for all future time intervals. This behavior for the intermediate flow modeled is explained by a higher evapotranspiration rate in the month of February than at the present time, that overcomes the increase in precipitation. The methodology applied to the study of these streams can be applied in many other rivers of the world, to try to elucidate the future behavior and impact of climate change in river discharge and chemistry 2021-09-10 English text Ohio University / OhioLINK http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1620167556121952 http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1620167556121952 unrestricted This thesis or dissertation is protected by copyright: some rights reserved. It is licensed for use under a Creative Commons license. Specific terms and permissions are available from this document's record in the OhioLINK ETD Center. |
| collection |
NDLTD |
| language |
English |
| sources |
NDLTD |
| topic |
Geology Artificial Neural Network discharge acid mine drainage precipitation evapotranspiration climate change |
| spellingShingle |
Geology Artificial Neural Network discharge acid mine drainage precipitation evapotranspiration climate change Ajayi, Toluwaleke Modeling Discharge and Water Chemistry Using Artificial Neural Network |
| author |
Ajayi, Toluwaleke |
| author_facet |
Ajayi, Toluwaleke |
| author_sort |
Ajayi, Toluwaleke |
| title |
Modeling Discharge and Water Chemistry Using Artificial Neural Network |
| title_short |
Modeling Discharge and Water Chemistry Using Artificial Neural Network |
| title_full |
Modeling Discharge and Water Chemistry Using Artificial Neural Network |
| title_fullStr |
Modeling Discharge and Water Chemistry Using Artificial Neural Network |
| title_full_unstemmed |
Modeling Discharge and Water Chemistry Using Artificial Neural Network |
| title_sort |
modeling discharge and water chemistry using artificial neural network |
| publisher |
Ohio University / OhioLINK |
| publishDate |
2021 |
| url |
http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1620167556121952 |
| work_keys_str_mv |
AT ajayitoluwaleke modelingdischargeandwaterchemistryusingartificialneuralnetwork |
| _version_ |
1719480032501432320 |