Evaluating the Land Use and Land Cover Change Impact on Streamflow Kulfo Catchment
| dc.contributor.advisor | Abebe, Adane (PhD) | |
| dc.contributor.author | Anja, Assebe | |
| dc.date.accessioned | 2022-05-24T12:13:36Z | |
| dc.date.accessioned | 2023-11-18T09:52:25Z | |
| dc.date.available | 2022-05-24T12:13:36Z | |
| dc.date.available | 2023-11-18T09:52:25Z | |
| dc.date.issued | 2021-10-27 | |
| dc.description.abstract | Streamflow is one of the key components of the hydrological cycle that can be altered and/or modified by a variety of variables. One of the key variables is the change in LULC. In kulfo cathement, in Ethiopia's southern region, suitable LULC detection techniques were not addressed and evaluated yet, and also the changing of the exesting LULC is the main stress in the streamflow of the Kulfo catchment. As a result, the impact of LULC change on streamflow was assessed in this study using the soil and water assessment tool model. Sensitivity, calibration, and validation were also performed using historical streamflow data in SWAT-CUP (Calibration and Uncertainty program) using sequential uncertainty fitting–version 2 (SUFI-2). There were four different algorithms applied to classify the LULC change. The best performing of four distinct algorithms (SVM, CART, RF, and Navia's) available in the Google Earth Engine were compared, and the best performing was chosen to generate the time-series LULC maps of the research area (1986, 2000, 2016, and 2020). GCPs gathered in the field were used to assess the accuracy of these algorithms. To train and evaluate the LULC maps generated from the Google Earth Engine platform, high resolution (30m) Landsat imagery from the thematic mapper (TM), enhanced thematic mapper plus (ETM+), and operational land imager (OLI) were employed, along with historical trends and ground-based data. As a result, the SVM method outperformed the other algorithms in this study when it came to LULC classification. During the study's period, the area covered by vegetation declined from 18.81 % to 3.1 %, while agricultural land increased from 19.44 % to 57.12 % and shrub land decreased from 34.18 % to 14.73 %. As a result, the impact of these LULC variations on streamflow was assessed using the Soil & Water Assessment Tool (SWAT) model, and over the study's period, substantial mean monthly and seasonal streamflow variability was observed. Monthly, these variabilities were raised from 6.72 % to 7.85%. The year has been divided in to three seasons Kiremt, Belg, and Bega. Seasonally, streamflow has dropped for all seasons (Kiremt, Belg, and Bega) from 2016 to 2020, but it has increased from 2000 to 2016. (Kiremt, Belg, and Bega). The calibration results showed an acceptable range between observed and simulated streamflow (0.6, 0.8, 0.75, and 0.75 for NSE and 0.75, 0.76, 0.79, and 0.81 for R2). Validation findings for observed and simulated streamflow were similarly within acceptable limits (0.72, 0.6, 0.74, and 0.75 for NSE and 0.8, 0.75, 0.73, and 0.8 for R2). | en_US |
| dc.identifier.uri | http://etd.aau.edu.et/handle/12345678/31756 | |
| dc.language.iso | en | en_US |
| dc.publisher | Addis Ababa University | en_US |
| dc.subject | Google Earth Engine | en_US |
| dc.subject | Streamflow | en_US |
| dc.subject | SWAT | en_US |
| dc.subject | SWAT-CUP | en_US |
| dc.subject | Machine Learning | en_US |
| dc.subject | Kulfo | en_US |
| dc.title | Evaluating the Land Use and Land Cover Change Impact on Streamflow Kulfo Catchment | en_US |
| dc.type | Thesis | en_US |