Floods are some of the most destructive and catastrophic disasters worldwide. Development of management plans needs a deep understanding of the likelihood and magnitude of future flood events. The purpose of this research was to estimate flash flood susceptibility in the Tafresh watershed, Iran, using five machine learning methods, i.e., alternating decision tree (ADT), functional tree (FT), kernel logistic regression (KLR), multilayer perceptron (MLP), and quadratic discriminant analysis (QDA). A geospatial database including 320 historical flood events was constructed and eight geo-environmental variables—elevation, slope, slope aspect, distance from rivers, average annual rainfall, land use, soil type, and lithology—were used as flood influencing factors. Based on a variety of performance metrics, it is revealed that the ADT method was dominant over the other methods. The FT method was ranked as the second-best method, followed by the KLR, MLP, and QDA. Given a few differences between the goodness-of-fit and prediction success of the methods, we concluded that all these five machine-learning-based models are applicable for flood susceptibility mapping in other areas to protect societies from devastating floods.

No abstract

No abstract

No abstract

No abstract

Mapping landscape variation in tree species richness (SR) is essential to the long term management and conservation of forest ecosystems. The current study examines the prospect of mapping field assessments of SR in a high-elevation, deciduous forest in northern Iran as a function of 16 biophysical variables representative of the area’s unique physiography, including topography and coastal placement, biophysical environment, and forests. Basic to this study is the development of moderate-resolution biophysical surfaces and associated plot-estimates for 202 permanent sampling plots. The biophysical variables include: (i) three topographic variables generated directly from the area’s digital terrain model; (ii) four ecophysiologically-relevant variables derived from process models or from first principles; and (iii) seven variables of Landsat-8-acquired surface reflectance and two, of surface radiance. With symbolic regression, it was shown that only four of the 16 variables were needed to explain 85% of observed plot-level variation in SR (i.e., wind velocity, surface reflectance of blue light, and topographic wetness indices representative of soil water content), yielding mean-absolute and root-mean-squared error of 0.50 and 0.78, respectively. Overall, localised calculations of wind velocity and surface reflectance of blue light explained about 63% of observed variation in SR, with wind velocity accounting for 51% of that variation. The remaining 22% was explained by linear combinations of soil-water-related topographic indices and associated thresholds. In general, SR and diversity tended to be greatest for plots dominated by Carpinus betulus (involving ≥ 33% of all trees in a plot), than by Fagus orientalis (median difference of one species). This study provides a significant step towards describing landscape variation in SR as a function of modelled and satellite-based information and symbolic regression. Methods in this study are sufficiently general to be applicable to the characterisation of SR in other forested regions of the world, providing plot-scale data are available for model generation.

The diameters and heights of trees are two of the most important components in a forest inventory. In some circumstances, the heights of trees need to be estimated due to the time and cost involved in measuring them in the field. Artificial intelligence models have many advantages in modeling nonlinear height–diameter relationships of trees, which sometimes make them more useful than empirical models in estimating the heights of trees. In the present study, the heights of trees in uneven-aged and mixed stands in the high elevation forests of northern Iran were estimated using an artificial neural network (ANN) model, an adaptive neuro-fuzzy inference system (ANFIS) model, and empirical models. A systematic sampling method with a 150 × 200 m network (0.1 ha area) was employed. The diameters and heights of 516 trees were measured to support the modeling effort. Using 10 nonlinear empirical models, the ANN model, and the ANFIS model, the relationship between height as a dependent variable and diameter as an independent variable was analyzed. The results show, according to R2, relative root mean square error (RMSE), and other model evaluation criteria, that there is a greater consistency between predicted height and observed height when using artificial intelligence models (R2 = 0.78; RMSE (%) = 18.49) than when using regression analysis (R2 = 0.68; RMSE (%) = 17.69). Thus, it can be said that these models may be better than empirical models for predicting the heights of common, commercially-important trees in the study area.

No abstract