Abstract. The Support Vector Machine (SVM) is a theoretically superior machine learning methodology with great results in classification of remotely sensed datasets. Determination of optimal parameters applied in SVM is still vague to some scientists. In this research, it is suggested to use the Taguchi method to optimize these parameters. The objective of this study was to detect tree crowns on very high resolution (VHR) aerial imagery in Zagros woodlands by SVM optimized by Taguchi method. A 30 ha plot of Persian oak (Quercus persica) coppice trees was selected in Zagros woodlands, Iran. The VHR aerial imagery of the plot with 0.06 m spatial resolution was obtained from National Geographic Organization (NGO), Iran, to extract the crowns of Persian oak trees in this study. The SVM parameters were optimized by Taguchi method and thereafter, the imagery was classified by the SVM with optimal parameters. The results showed that the Taguchi method is a very useful approach to optimize the combination of parameters of SVM. It was also concluded that the SVM method could detect the tree crowns with a KHAT coefficient of 0.961 which showed a great agreement with the observed samples and overall accuracy of 97.7% that showed the accuracy of the final map. Finally, the authors suggest applying this method to optimize the parameters of classification techniques like SVM.
تحلیل توزیع مکانی گیاهان چوبی در مناطق خشک و نیم هخشک، کنشهای متقابل آنها و چگونگی تأثیرشان بر یکدیگر را توضیح میدهد. این پژوهش با هدف ارزیابی کنش های متقابل درون گونه ای درختچه های اشنان (Seidlitzia rosmarinus) در مناطق خشک مرکزی ایران با استفاده از آماره های اختصاری مختلف (تابع همبستگی جفتی g(r)، تابع O-ring O(r)، تابع توزیع نزدیکترین همسایه D(r)، تابع توزیع تماس کرویHs(r) و تابع همبستگی نشاندار kmm(r)) انجام شد. یک قطعه نمونه با ابعاد 160 × 160 متر که به طور خالص پوشیده از اشنان بود، در منطقه حفاظت‌شده قهی استان اصفهان انتخاب شد. نقشه نقطه ای تمام 989 درختچه اشنان با استفاده از سامانه موقعیت یاب جهانی تفاضلی سه‌فرکانسه تریمبل R8 با دقت سه میلی متر ± 0/1 پی پی ام تهیه شد. مقایسه با فرآیند پوآسون ناهمگن نشان داد که الگوی مشاهده شده درختچه ها دارای ناهمگنی مکانی معنی دار (در سطح اطمینان 95 درصد) بود. نتایج g(r) و O(r) نشاندهنده تجمع معنی دار (در سطح اطمینان 95 درصد) درختچه های اشنان تا فاصله سه متر در کنار یکدیگر بود. نتایج D(r) و Hs(r) نیز نشان داد که بیشترین فاصله تا نزدیکترین درختچه شش متر بود و توزیع اندازه فضاهای خالی تا این مقیاس به طور معنی داری با توزیع تصادفی تفاوت داشت. درنهایت، kmm(r) برای ارتفاع، قطر متوسط تاج و مساحت تاج همبستگی مثبت ویژگی های زیست سنجی اشنان ها را نشان داد. به طور کلی، نتیجه گیری شد که در منطقه مورد مطالعه بین پایه های گروهی اشنان یک کنش متقابل مثبت وجود دارد که با توجه به اثر تسهیل کنندگی درون گونه ای آنها بر یکدیگر در کنار هم تجمع کرده اند.
Anthropogenic industrial dust decreases productivity and slows down the growth of plants. Quantifying the effects of industrial dust on vegetation and determining the distance over which factories scatter dust are of paramount importance for biodiversity conservation and sustaining ecosystem services. This study aims at quantifying the effect of dust emitted by the Neka cement plant (NCP), Mazandaran province, northern Iran, on the surrounding Hyrcanian forests based on an analysis of the Leaf Area Index (LAI) retrieved from Sentinel-2 imagery. An Inductively Coupled Plasma Mass Spectrometer (ICP-MS) was used to quantify the concentrations of cadmium (Cd), chromium (Cr), copper (Cu), lead (Pb), calcium (Ca), magnesium (Mg), sodium (Na), silicon (Si) and zinc (Zn) in leaves of the dominant Chestnut-leaved Oak (Quercus castaneifolia). A feed-forward neural network algorithm and field measurements were used to retrieve the leaf area index (LAI) from Sentinel-2 data with a RMSE of 0.42 (m2/m2). MODIS-NDVI and EVI time series spanning 17 years (2000 to 2017) were analysed to ensure the independence of the variation in the condition of the vegetation from drought or other environmental factors. The results indicate that Sentinel-2 data can be used to map degradation due to pollution from the cement plant and quantify the effect of the dust spatially. Dust from the cement plant (dust source) was carried approximately 4700 meters in the direction of the prevailing wind. A significant correlation of 0.849 was recorded between LAI and distance from the NCP. It is concluded that dust from the NCP had adverse ecological effects on the neighbouring forest ecosystems recently designated a UNESCO World Heritage Site.
Studying spatial patterns and habitat association of plant communities may provide understanding of the ecological mechanisms and processes that maintain species coexistence. To conduct assessments of correlation between community compositions and habitat association, we used data from two topographically different plots with 2 ha area in tropical evergreen forests with the variables recorded via grid systems of 10 × 10 m subplots in Northern-Central Vietnam. First, we tested the relationship between community composition and species diversity indices considering the topographical variables. We then assessed the interspecific interactions of 20 dominant plant species using the nearest-neighbor distribution function, Dij(r), and Ripley’s K-function, Kij(r). Based on the significant spatial association of species pairs, indices of interspecific interaction were calculated by the quantitative amounts of the summary statistics. The results showed that (i) community compositions were significantly influenced by the topographic variables and (ii) almost 50% significant pairs of species interactions were increased with increasing spatial scales up to 10–15 m, then declined and disappeared at scales of 30–40 m. Segregation and partial overlap were the dominant association types and disappeared at larger spatial scales. Spatial segregation, mixing, and partial overlap revealed the important species interactions in maintaining species coexistence under habitat heterogeneity in diverse forest communities.
'%3e%3cg id='e'%3e%3cg id='c' fill='none' stroke='%23fff' stroke-width='2'%3e%3cpath id='b' d='M0 1h26M1 10V5h8v4h8V5h-5M4 9h2m20 0h-5V5h8m0-5v9h8V0m-4 0v9' transform='scale(1.4)'/%3e%3cpath id='a' d='M0 7h9m1 0h9' transform='scale(2.8)'/%3e%3cuse xlink:href='%23a' y='120'/%3e%3cuse xlink:href='%23b' y='145.2'/%3e%3c/g%3e%3cg id='d'%3e%3cuse xlink:href='%23c' x='56'/%3e%3cuse xlink:href='%23c' x='112'/%3e%3cuse xlink:href='%23c' x='168'/%3e%3c/g%3e%3c/g%3e%3cuse xlink:href='%23d' x='168'/%3e%3cuse xlink:href='%23e' x='392'/%3e%3c/g%3e%3cg fill='%23da0000' transform='matrix(45 0 0 45 315 180)'%3e%3cg id='f'%3e%3cpath d='M-.548.836A.912.912 0 0 0 .329-.722 1 1 0 0 1-.548.836'/%3e%3cpath d='M.618.661A.764.764 0 0 0 .422-.74 1 1 0 0 1 .618.661M0 1l-.05-1L0-.787a.31.31 0 0 0 .118.099V-.1l-.04.993zM-.02-.85 0-.831a.144.144 0 0 0 .252-.137A.136.136 0 0 1 0-.925'/%3e%3c/g%3e%3cuse xlink:href='%23f' transform='scale(-1 1)'/%3e%3c/g%3e%3c/svg%3e)
'%3e%3cpath id='a' fill='%23FF0' d='M0 0v6h4' transform='rotate(18)'/%3e%3cuse xlink:href='%23a' transform='scale(-1 1)'/%3e%3c/g%3e%3cg id='c' transform='rotate(72)'%3e%3cuse xlink:href='%23b'/%3e%3cuse xlink:href='%23b' transform='rotate(72)'/%3e%3c/g%3e%3cuse xlink:href='%23c' transform='scale(-1 1)'/%3e%3c/svg%3e)
