Skip to main content
ARS Home » Plains Area » Las Cruces, New Mexico » Range Management Research » Research » Publications at this Location » Publication #307798

Title: Predicting total organic carbon load with El Nino southern oscillation phase using hybrid and fuzzy logic approaches

Author
item SHARMA, SURESH - Youngstown Air Research Station
item SRIVASTAVA, PUNEET - Auburn University
item KALIN, LATIF - Auburn University
item FANG, XING - Auburn University
item ELIAS, EMILE - New Mexico State University

Submitted to: Transactions of the ASABE
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 6/19/2014
Publication Date: N/A
Citation: N/A

Interpretive Summary: Total organic carbon (TOC) load in the Southeast can be affected by the El Niño Southern Oscillation (ENSO)-induced climate variability. Since ENSO can be forecasted a few months in advance, ENSO-based TOC load forecasts can be used to tailor additional treatment required for TOC removal (e.g., activated carbon) before chlorination, thus reducing treatment costs. The objectives of this study were to quantity the effect of ENSO on watershed TOC loads and develop data-driven modeling approaches for forecasting TOC loads.

Technical Abstract: During drinking water treatment chlorine reacts with total organic carbon (TOC) to form disinfection byproducts (DBP), some of which can be carcinogenic. Additional treatment required to remove TOC before chlorination significantly increases treatment cost. There are two main sources of TOC in a water supply reservoir: (1) the watershed draining to the reservoir, and 2) the internal loading within the reservoir. Out of the two sources, watershed TOC load can be significant especially when the watershed has large wetland area. TOC load in the Southeast can be affected by the El Niño Southern Oscillation (ENSO)-induced climate variability. Since ENSO can be forecasted a few months in advance, ENSO-based TOC load forecasts can be used to tailor additional treatment required for TOC removal (e.g., activated carbon) before chlorination, thus reducing treatment costs. The objectives of this study were to quantity the effect of ENSO on watershed TOC loads and develop data-driven modeling approaches for forecasting TOC loads. Four hybrid and four fuzzy logic models, with different model architectures, were developed for forecasting watershed TOC loads using temperature, precipitation, Niño 3.4, and Trans Niño Index (TNI). The study concludes that the hybrid models are suitable for estimating real-time TOC loads, while the fuzzy logic models are suitable for qualitative forecasting of TOC loads with one-month lead time. In addition, the study highlights the importance of incorporating ENSO information into the data-driven models in ENSO-affected regions.