جنگل زدایی

Global forest area has decreased by nearly 180 million ha in three decades. So, many ecosystem services provided by forests have been threatened. Reforestation and afforestation are the most effective strategies for mitigating deforestation. Therefore, in a variety of countries worldwide, including Iran, several afforestation projects have been implemented; however, the quantity and quality of many afforested lands have decreased over time under the influence of catastrophic factors, environmental stress, and different management methods. Awareness and continuous monitoring of forest programs are some of the most fundamental forestry policies. Therefore, the monitoring of annual afforestation in the eastern Golestan province using Google Earth software was put on the agenda to prepare an afforestation map and identify the reasons for the success and failure of the implemented plans. According to the findings, 19,377.39 ha of afforestation have been planted in Golestan province. Of these, Maraveh Tappeh city has the highest amount of afforestation with more than 9,256 ha with C. arizonica L, C. sempervirens L. var. horizontalis (Mill.) Gord. and P. brutia Ten, mostly. The presence of suitable climatic and edaphic conditions in the Golidagh of Maraveh Tappeh City and the ArabDagh area of Kalaleh City played a prominent role in the success of artificial forests in these areas. It should be noted that wood smuggling, the presence of livestock, the occurrence of fires, the presence of natural and human obstacles, and continuous monitoring have been other factors affecting the success or failure of afforestation programs in the eastern Golestan province.

The change in forest cover plays a vital role in ecosystem services, atmospheric carbon balance and thus climate change. The goal of this study is comparison of three procedure of Artificial Neural Network, Logistic regression and Similarity weighted Instance-based Learning (SIM Weight) to predict spatial trend of forest cover change.

In this study, land use maps for the periods 1984 and 2012 derived from Landsat TM satellite imagery, was used. Transition potential modeling using artificial neural network, Logistic regression and Similarity weighted Instance-based Learning and prediction based on the best model using Markov chain model was performed. In order to assess the accuracy of modeling, statistics of relative performance characteristic (ROC), ratio Hits/False Alarms and figure of merit was used.

The results show the accuracy of artificial neural network with the ROC equal to 0.975, the ratio Hits/False Alarms equal to 63 percent and the figure of merit is equal to 12 percent.

 Discussion and Conclusions

Artificial Neural Networks in comparison with Logistic Regression and Similarity weighted Instance-based Learning has higher accuracy and less error in modeling and predicting of forest changes.