Dr. Mirac KILIC

This research introduces a scientific methodology to identify areas affected by gully erosion using Geographic Object Based Image Analysis (GEOBIA) and Random Forest (RF) supervised machine learning. The GEOBIA and RF were applied in Besni district, which has a Mediterranean climate, of Adiyaman province in Turkey by including many factors in the model. Estimation Scale Parameter (ESPII) algorithm was used in the segmentation phase. The novelty of this study is the implementation of RF supervised classification algorithm to classify a large number of objects determined after the segmentation process, due to the large size of the study area. Therefore, open access data has been evaluated with high classification accuracy without the need for labor. Precision, Recall and F1-Score values were calculated using true positive (TP), true negative (TN), false positive (FP) and false negative (FN) values based on field observations and Google Earth images of the study area. The TP, TN, FP and FN values were 0.90, 0.95 and 0.92, respectively. In addition, a Kappa-index was calculated as 0.88. The gully erosion map obtained using aforementioned methodology can be used to take necessary measures to prevent further degradation and plan sustainable land uses.

About Me

Dr Mirac Kilic is an Assistant Professor of Soil Science at Malatya Turgut Ozal University, Turkey. He integrates digital soil mapping, remote sensing and machine learning to support climate-smart land management in Mediterranean drylands. Since finishing his PhD in 2023 on land-use change impacts, he has authored 15+ SCI papers. Recent work compares kriging with tree-based learners for soil pH–EC mapping (MAS Applied Sci., 2024), uses boosted regression and Sentinel-2 for organic carbon stock estimation (Environ. Sci. Pollut. Res., 2023), and applies CNN-driven gully detection in GEOBIA workflows (Geocarto Int., 2022). He has also co-developed integrated land-suitability frameworks linking land capability, NDVI and degradation sensitivity (Env. Dev. Sustain., 2024) and rapeseed suitability modelling with fuzzy logic (Ind. Crops Prod., 2024). Kilic supervises projects on soil fertility in pistachio orchards and forensic soil spectroscopy, and lectures on sustainable agriculture, GIS and AI. Certified in AI (200 h) and UAV operations, he codes in Python, Google Earth Engine and GIS toolchains such as Rasterio, GeoPandas, scikit-learn and TensorFlow. Current interests include explainable ML, spatio-temporal trend analysis with LandTrendr, and coupling Earth system model outputs with deep neural networks to predict hydraulic conductivity, soil organic carbon and erosion risk under CMIP6 scenarios.

Dr. Mirac KILIC

Dr. Mirac KILIC

Research Focus & Metrics

Academic Career Length

Publication Type Breakdown

Representative Publications

About Me