مدل سازی زوال درختان بلوط با استفاده از شبکه های عصبی مصنوعی

جنگل های زاگرس بیشترین تاثیر را در تامین آب، حفظ خاک و تعدیل آب  و هوای کشور دارد. با این وجود بخش قابل توجهی از این جنگل ها دچار پدیده ی زوال درختان بلوط شده است. مشخص نبودن پارامترهای موثر در زوال و نحوه ی ارتباط پارامترها، از جمله عواملی هستند که باعث سخت تر شدن شناخت و مدل سازی این پدیده می شود. هدف این پژوهش تعیین پارامترهای تاثیرگذار برای مدل سازی زوال درختان بلوط و مدل سازی این پدیده با استفاده از شبکه های عصبی مصنوعی در استان لرستان است. در این پژوهش، پارامترهای دما، بارش، ارتفاع، شیب، جهت، نوع خاک و میزان ریزگردها به عنوان پارامترهای اولیه انتخاب شدند. همچنین از عملگرهای ضرب، لگاریتم، تبدیلات هذلولی و آنالیز مولفه های اصلی برای ترکیب پارامترها استفاده شد. به دلیل معلوم نبودن نحوه ی ارتباط و میزان اثر هر پارامتر، از شبکه های عصبی مصنوعی برای مدل سازی پدیده زوال استفاده شد. در مجموع 385 ترکیب مختلف از پارامترهای اولیه، با استفاده از عملگرهای فوق تولید و در سه معماری پیش خور با سه لایه پنهان، احتمالاتی و معماری ماشین بردار پشتیبان در شبکه های عصبی، (در مجموع تعداد 1155 شبکه ی عصبی) ارزیابی شد. نتایج ارزیابی نشان داد معماری احتمالاتی (0.87=r) با ورودی های ارتفاع، جهت، شیب، ریز گرد، نوع خاک و مولفه ی اصلی (بارش و دما) بهترین عملکرد را در مدل سازی زوال درختان بلوط دارد. با توجه به نتایج، استفاده از شبکه های عصبی مصنوعی احتمالاتی در شرایط عدم قطعیت و وجود دانش جزئی از پدیده، توصیه می شود. همچنین نتایج نشان دادند که استفاده از مولفه ی اصلی پارامترهای دما و بارش، استرس ناشی از خشکی را بهتر مدل می کند. استفاده از ترکیب بهینه ی پارامترها، در مدل احتمالاتی نسبت به ترکیب عادی، باعث افزایش 0.05 ضریب همبستگی شد.

Modeling oak decline using artificial neural networks

Extended AbstractIntroductionOak is a common species in Iran and the most important one in Zagros forests. Zagros forests play a crucial and effective role in water supply, soil conservation and climate modification in Iran. Unfortunately, a significant part of those forests suffer from oak decline. Oak decline (or oak mortality) is a widespread phenomenon in oak forests around the world, which has gained the attention of many researchers in forestry over the past decade. In Iran, this phenomenon was first observed in Zagros forests in 2013. Factors affecting oak decline and their mutual interactions are not clearly identified, which makes understanding and modeling of these processes challenging. Only a few studies have been performed in relation to this phenomenon in Iran. Thus, we chose to determine the most effective parameters and find the best modeling method for oak decline in Iran and especially in Lorestan province.Materials & MethodsIn order to find effective environmental variables, related literature review was thoroughly investigated. Environmental parameters including temperature, precipitation, elevation, slope, direction, soil type, and amount of aerosols were selected as basic influencing parameters. All parameters were then interpolated to produce raster data with 30meter cell resolution. To find the optimal combination of the parameters, four operators including multiplication, logarithm, hyperbolic transformations, and principal component analysis (PCA) were used. A total 385 different combinations of the influencing parameters were produced using the above mentioned operators. The relation and weight of each parameter are unknown, thus Artificial Neural Networks were used to model oak decline process. Three feed forward artificial neural network, including Backpropagation Neural Network (BP), Probabilistic neural network (PNN) and Support Vector Neural Network (SVNN) were selected as modeling methods. Then, 385 different combinations of the influencing parameters were used in the above mentioned models. To train and evaluate each neural network, a total number of 10000 samples were randomly selected from the study area. 70 percent of these random samples were used to train, 15 percent to evaluate and 15 percent to validate the models. Also, crossvalidation method was used to avoid over fitting of neural networks. Finally, 1155 created NN models were compared using R parameter to find the best configuration for modeling oak decline and identifying the most influential environmental parameters in oak decline.Results & Discussion Evaluating 1155 different networks indicated that Probabilistic neural network (R=0.87) with 6 inputs, including 1) elevation, 2) slope, 3) direction, 4) aerosols, 5) soil type and 6) principal component of temperature and precipitation, performed better than SVNN and BP in modeling oak decline. Moreover, using different combinations of influencing factors improved the results and increased correlation coefficient (R) of optimal inputs by 0.05 as compared to initial inputs. Thus, it can be concluded that increased number of inputs does not necessarily guarantee a better performance. Furthermore, two principle parameters of temperature and perception have a more significant role in modelling drought stress as compared to other parameters.ConclusionOak decline is a complicated phenomenon and different factors contribute to its occurrence. The present study investigates all environmental parameters affecting oak decline through a comprehensive literature review. Results indicate appropriate performance of probabilistic neural networks in modeling oak decline. Moreover, principal component analysis is considered to be a useful tool for modeling of drought stress in oak trees. Due to different accuracy and precision of these neural networks, it is necessary to evaluate different configurations. For further researches, it is suggested to use other parameters, such as distance from population centers, water table, age of oak trees, oak tree height and characteristics of other nearby trees.