Prediction of Plant Diversity Using Multi-Seasonal Remotely Sensed and Geodiversity Data in a Mountainous Area

Plant diversity measurement and monitoring are required for reversing biodiversity loss ensuring sustainable management. Traditional methods have been using in situ measurements to build multivariate models connecting environmental factors species diversity. Developments remotely sensed datasets, processing techniques, machine learning provide new opportunities assessing relevant parameters estimating In this study, geodiversity variables containing the topographic soil multi-seasonal remote-sensing-based features were used estimate plant a rangeland from southwest Iran. Shannon’s Simpson’s indices, richness, vegetation cover measure attributes 96 plots. A random forest model was implemented predict map 32 21 variables. Additionally, linear regression Spearman’s correlation coefficient assess relationship between spectral diversity, expressed as of variation metrics. The results indicated that synergistic use highest accuracy Shannon, Simpson, indices (R2 up 0.57), compared single each date (February, April, July). Furthermore, strongest based on remotely-sensed data April. approach multi-model evaluations full could be useful method monitoring.