Low-Flow (7-Day, 10-Year) Classical Statistical and Improved Machine Learning Estimation Methodologies
Water resource managers require accurate estimates of the 7-day, 10-year low flow (7Q10) of streams for many reasons, including protecting aquatic species, designing wastewater treatment plants, and calculating municipal water availability. StreamStats, a publicly available web application developed...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/15/15/2813 |
| _version_ | 1797585934641790976 |
|---|---|
| author | Andrew DelSanto Md Abul Ehsan Bhuiyan Konstantinos M. Andreadis Richard N. Palmer |
| author_facet | Andrew DelSanto Md Abul Ehsan Bhuiyan Konstantinos M. Andreadis Richard N. Palmer |
| author_sort | Andrew DelSanto |
| collection | DOAJ |
| description | Water resource managers require accurate estimates of the 7-day, 10-year low flow (7Q10) of streams for many reasons, including protecting aquatic species, designing wastewater treatment plants, and calculating municipal water availability. StreamStats, a publicly available web application developed by the United States Geologic Survey that is commonly used by resource managers for estimating the 7Q10 in states where it is available, utilizes state-by-state, locally calibrated regression equations for estimation. This paper expands StreamStats’ methodology and improves 7Q10 estimation by developing a more regionally applicable and generalized methodology for 7Q10 estimation. In addition to classical methodologies, namely multiple linear regression (MLR) and multiple linear regression in log space (LTLR), three promising machine learning algorithms, random forest (RF) decision trees, neural networks (NN), and generalized additive models (GAM), are tested to determine if more advanced statistical methods offer improved estimation. For illustrative purposes, this methodology is applied to and verified for the full range of unimpaired, gaged basins in both the northeast and mid-Atlantic hydrologic regions of the United States (with basin sizes ranging from 2–1419 mi<sup>2</sup>) using leave-one-out cross-validation (LOOCV). Pearson’s correlation coefficient (R<sup>2</sup>), root mean square error (RMSE), Kling–Gupta Efficiency (KGE), and Nash–Sutcliffe Efficiency (NSE) are used to evaluate the performance of each method. Results suggest that each method provides varying results based on basin size, with RF displaying the smallest average RMSE (5.85) across all ranges of basin sizes. |
| first_indexed | 2024-03-11T00:13:41Z |
| format | Article |
| id | doaj.art-931f2678ecae41a3bc6aef4227b0360a |
| institution | Directory Open Access Journal |
| issn | 2073-4441 |
| language | English |
| last_indexed | 2024-03-11T00:13:41Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Water |
| spelling | doaj.art-931f2678ecae41a3bc6aef4227b0360a2023-11-18T23:48:06ZengMDPI AGWater2073-44412023-08-011515281310.3390/w15152813Low-Flow (7-Day, 10-Year) Classical Statistical and Improved Machine Learning Estimation MethodologiesAndrew DelSanto0Md Abul Ehsan Bhuiyan1Konstantinos M. Andreadis2Richard N. Palmer3Department of Civil and Environmental Engineering, University of Massachusetts, Amherst, MA 01003, USADepartment of Civil and Environmental Engineering, University of Massachusetts, Amherst, MA 01003, USADepartment of Civil and Environmental Engineering, University of Massachusetts, Amherst, MA 01003, USADepartment of Civil and Environmental Engineering, University of Massachusetts, Amherst, MA 01003, USAWater resource managers require accurate estimates of the 7-day, 10-year low flow (7Q10) of streams for many reasons, including protecting aquatic species, designing wastewater treatment plants, and calculating municipal water availability. StreamStats, a publicly available web application developed by the United States Geologic Survey that is commonly used by resource managers for estimating the 7Q10 in states where it is available, utilizes state-by-state, locally calibrated regression equations for estimation. This paper expands StreamStats’ methodology and improves 7Q10 estimation by developing a more regionally applicable and generalized methodology for 7Q10 estimation. In addition to classical methodologies, namely multiple linear regression (MLR) and multiple linear regression in log space (LTLR), three promising machine learning algorithms, random forest (RF) decision trees, neural networks (NN), and generalized additive models (GAM), are tested to determine if more advanced statistical methods offer improved estimation. For illustrative purposes, this methodology is applied to and verified for the full range of unimpaired, gaged basins in both the northeast and mid-Atlantic hydrologic regions of the United States (with basin sizes ranging from 2–1419 mi<sup>2</sup>) using leave-one-out cross-validation (LOOCV). Pearson’s correlation coefficient (R<sup>2</sup>), root mean square error (RMSE), Kling–Gupta Efficiency (KGE), and Nash–Sutcliffe Efficiency (NSE) are used to evaluate the performance of each method. Results suggest that each method provides varying results based on basin size, with RF displaying the smallest average RMSE (5.85) across all ranges of basin sizes.https://www.mdpi.com/2073-4441/15/15/2813machine learningstatistical methodshydrologyextreme hydrologic eventslong-term forecasting |
| spellingShingle | Andrew DelSanto Md Abul Ehsan Bhuiyan Konstantinos M. Andreadis Richard N. Palmer Low-Flow (7-Day, 10-Year) Classical Statistical and Improved Machine Learning Estimation Methodologies Water machine learning statistical methods hydrology extreme hydrologic events long-term forecasting |
| title | Low-Flow (7-Day, 10-Year) Classical Statistical and Improved Machine Learning Estimation Methodologies |
| title_full | Low-Flow (7-Day, 10-Year) Classical Statistical and Improved Machine Learning Estimation Methodologies |
| title_fullStr | Low-Flow (7-Day, 10-Year) Classical Statistical and Improved Machine Learning Estimation Methodologies |
| title_full_unstemmed | Low-Flow (7-Day, 10-Year) Classical Statistical and Improved Machine Learning Estimation Methodologies |
| title_short | Low-Flow (7-Day, 10-Year) Classical Statistical and Improved Machine Learning Estimation Methodologies |
| title_sort | low flow 7 day 10 year classical statistical and improved machine learning estimation methodologies |
| topic | machine learning statistical methods hydrology extreme hydrologic events long-term forecasting |
| url | https://www.mdpi.com/2073-4441/15/15/2813 |
| work_keys_str_mv | AT andrewdelsanto lowflow7day10yearclassicalstatisticalandimprovedmachinelearningestimationmethodologies AT mdabulehsanbhuiyan lowflow7day10yearclassicalstatisticalandimprovedmachinelearningestimationmethodologies AT konstantinosmandreadis lowflow7day10yearclassicalstatisticalandimprovedmachinelearningestimationmethodologies AT richardnpalmer lowflow7day10yearclassicalstatisticalandimprovedmachinelearningestimationmethodologies |