---

Land use maps are the most essential tools and information in the hand of natural resources managers. Over the last years, many applications of neural network classifiers for land use classification have been reported in the literature, but few studies have assessed the use of decision tree classifiers and their comparison. In this study, first, geometric and radiometric corrections were performed on ETM+ data. Then, with field surveying, the various land cover classes were defined and training areas were selected. The main objective of this study is to compare three artificial neural network methods for land cover classification in Daresher catchment of Ilam province. Meanwhile, the performance of these algorithms has been compared with that obtained using decision tree (with three siplitting methods). The obtained results of accuracy assessment of the classified images showed that neural network classification methods (except Kohonen method) outperformed with overall mean accuracy of 92 and Kappa coefficient of 0.90 than by decision tree with mean overall mean accuracy of 90 and Kappa coefficient of 0.88. In addition, when different neural networks classifiers were analysed, fuzzy artmap approach outperformed than by perceptron multi-layer and Konohon classifiers in terms of overall Kappa coefficient accuracies (with more overall accuracies of %2, %22 and Kappa coefficients of %3 and %24). The highest accuracy of artificial neural network was with fuzzy artmap method. So, this study confirms efficiency and capability of artificial neural network methods for land cover classification.

---

 The plant and animal reserve of Zagros vegetation area has always been threatened and destroyed by fire in dry seasons. The lack of advanced surveying facilities has caused the location and extent of fire destruction to be recorded, as well as their impact on plant and animal species. Fire records are a good source of information in terms of reproducibility, fire-prone species, and the extent of restoration of damage caused by fires to be used in fire risk zoning and fire range expansion modeling. In this research, the methodology of discovering the traces of old fires has been discussed. This process has been done using Landsat 8 images. Various object-oriented algorithms and fuzzy membership functions have been used in image classification to detect fire damage. The accuracy of the classification is evaluated with the new QADI index. The introduction of the combined use of the near-infrared change percentage index and the NBRI47 burn index along with the use of Large, MS-Large fuzzy functions as the best classification method is one of the findings of this research. Kappa value in this method was calculated as 0.96, overall accuracy as 0.98, and Cadi value as 0.01. The area of the map resulting from the best classification showed the occurrence of a fire with an area of 62.75 hectares, which was confirmed by NASA fire detection systems and ground data. The methodology and results of this research, in addition to the possibility of being used in the scientific community of remote sensing, are also important for experts and planners of natural resources and the environment.