BUĞDAY, E.; ERKAN BUĞDAY, S. Modeling and simulating land use/cover change using artificial neural network from remotely sensing data. CERNE, v. 25, n. 2, p.246-254, 2019. HIGHLIGHTSApplicability of decision support systems in landscape planning.To reveal the spatio-temporal land use and land cover changes.Estimation of land use and cover change by human population movements. ABSTRACTIncreasing population, mobility and requirements of human beings have significant effects on the dynamics of land use and land cover. Today, these impacts need to be understood and analyzed for the applicability of decision support systems, which are an important tool in the management of natural resources, urban and rural areas. The aim of this study is to detect the temporal and spatial changes of land cover and human population, in northwest Turkey. For this purpose, using satellite images of 1997-2007 and 2017 years' land cover was estimated for 2027 by ANN (Artificial Neural Network) approach. Kappa values are 93%, 87% and 95% for 1997, 2007 and 2017 respectively. As a result, learning success was 80.6%, and correctness validation value was 90.1% for 2027 simulation. In parallel, the spatial analysis of the population was conducted for 2000-2007-2017. Using the exponential rate of change; the population was predicted to increase by concentrating on the urban area and the rural areas surrounding the urban (with a rate of 2.019%) for 2027. According to the results; rural population, urban population, forest, and built-up areas is estimated to increase by 4.14%, 5.58%, 2.72%, and 0.77% respectively from 2017 to 2027, while the agricultural and water area is estimated to decrease by 3.47% and 0.02% respectively. Consequently, the observation of population movements and the use of the ANN approach in simulations could be suggested for the success of planning in forest and land management.v.25 n.

The forests in Turkey is classified and managed according to their functions within the framework of Ecosystem Based MultiPurpose Planning policy. It is very important to ensure that planning activities are handled appropriately in order to carry out forestry activities which are labor intensive, difficult and dangerous. Forest roads have served as the main infrastructure facility for forestry activities in accordance with multiple purposes. In order to increase efficiency within the concept of precision forestry and to transfer the plans to the application more clearly, it is essential to use technology and technological machinery. In this context, this study aimed to reveal the capabilities of using Unmanned Aerial Vehicles (UAVs) and Geographical Information Systems (GIS) tools in planning the forest road construction. For this purpose, cut and fill volume of a 300 m long sample road was computed by using USGS based Digital Elevation Model (DEM) with 1 m x 1 m resolution and UAV based DEM with 0.05 m x 0.05 m resolution which were generated prior to road construction and after the road construction, respectively. The results indicated that the cut volume and fill volume were 81804.4 m 3 and 74.2 m 3 , respectively. It was found that the use of UAV will be quite advantageous in terms of capturing high quality and high-resolution data for planning the forest road construction and evaluating alternative routes.

Šumske ceste jedna su od temeljnih infrastruktura u obavljanju šumarskih djelatnosti i usluga. Budući da su šume općenito smještene u planinskim područjima sa strmim nagibom u Turskoj, teškoće koje se događaju u ovim planinskim uvjetima povećavaju troškove. Cilj ove studije je procijeniti alternative planiranja šumskih cesta koje će se razvijati u planinskim područjima koja se nalaze na osjetljivim klizištima, na temelju mapiranja mapa osjetljivosti na terenu (LSM). U tu svrhu generirano je ukupno 12 modela s različitim pristupima višestrukog odlučivanja (MCDM), uključujući Modificirani analitički hijerarhijski proces (M-AHP), Fuzz sustav (FIS) i logističku regresiju (LR). Kao rezultat studije, najbolji model bio je Model 3 dobiven uz LR pristup (područje ispod krivulje (AUC) = 76,6%), a zatim LR-Model 4 (AUC = 75,7%) i FIS-Model 4 (AUC = 73.4%). Model 3 (AUC = 71%) bio je najuspješniji M-AHP pristup. Slijedom toga, primjena ovih metoda pružit će prednost u donošenju točnijih i racionalnih odluka tijekom planiranja cestovne mreže u osjetljivim šumskim područjima.

No abstract

The effective management of forest resources is very important for the future of the forest and to meet both ecological and economic needs. In this study, it is aimed to contribute to the applicability of modeling in practice by identifying regions that may be landslide in forest areas via different modeling approaches. A total of six models were created by using four criteria (elevation, slope, aspect and stream power index) and using Fuzzy Inference System (FIS) and Modified-Analytic Hierarchy Process (M-AHP) approaches in this study. The model's performance was measured using the Receiver Operating Characteristic (ROC) curve and Area Under Curve (AUC). According to the results of study, the most successful model was determined as FIS Model 1 with the AUC value of 82.1% and M-AHP Model 1 with the AUC value of 80.9%. This study provides important outputs that indicates the potential benefits of using landslide susceptibility mapping in the fields of forest harvesting, road network planning and forest management.