Accurate and real-time land use/land cover (LULC) maps are important to provide precise information for dynamic monitoring, planning, and management of the Earth. With the advent of cloud computing platforms, time series feature extraction techniques, and machine learning classifiers, new opportunities are arising in more accurate and large-scale LULC mapping. In this study, we aimed at finding out how two composition methods and spectral–temporal metrics extracted from satellite time series can affect the ability of a machine learning classifier to produce accurate LULC maps. We used the Google Earth Engine (GEE) cloud computing platform to create cloud-free Sentinel-2 (S-2) and Landsat-8 (L-8) time series over the Tehran Province (Iran) as of 2020. Two composition methods, namely, seasonal composites and percentiles metrics, were used to define four datasets based on satellite time series, vegetation indices, and topographic layers. The random forest classifier was used in LULC classification and for identifying the most important variables. Accuracy assessment results showed that the S-2 outperformed the L-8 spectral–temporal metrics at the overall and class level. Moreover, the comparison of composition methods indicated that seasonal composites outperformed percentile metrics in both S-2 and L-8 time series. At the class level, the improved performance of seasonal composites was related to their ability to provide better information about the phenological variation of different LULC classes. Finally, we conclude that this methodology can produce LULC maps based on cloud computing GEE in an accurate and fast way and can be used in large-scale LULC mapping.

Forest canopy cover (FCC) is an important ecological parameter of forest ecosystems, and is correlated with forest characteristics, including plant growth, regeneration, biodiversity, light regimes, and hydrological properties. Here, we present an approach of combining Sentinel-2 data, high-resolution aerial images, and machine learning (ML) algorithms to model FCC in the Hyrcanian mixed temperate forest, Northern Iran. Sentinel-2 multispectral bands and vegetation indices were used as variables for modeling and mapping FCC based on UAV ground truth to a wider spatial extent. Random forest (RF), support-vector machine (SVM), elastic net (ENET), and extreme gradient boosting (XGBoost) were the ML algorithms used to learn and generalize on the remotely sensed variables. Evaluation of variable importance indicated that vegetation indices including NDVI, NDVI-A, NDRE, and NDI45 were the dominant predictors in most of the models. Model accuracy estimation results showed that among the tested models, RF (R² = 0.67, RMSE = 18.87%, MAE = 15.35%) and ENET (R² = 0.63, RMSE = 20.04%, MAE = 16.44%) showed the best and the worst performance, respectively. In conclusion, it was possible to prove the suitability of integrating UAV-obtained RGB images, Sentinel-2 data, and ML models for the estimation of FCC, intended for precise and fast mapping at landscape-level scale.

Tree height and crown diameter are two common individual tree attributes that can be estimated from unmanned aerial vehicle (UAV) images thanks to photogrammetry and structure from motion. This research investigates the potential of low-cost UAV aerial images to estimate tree height and crown diameter. Two successful flights were carried out in two different seasons corresponding to leaf-off and leaf-on conditions to generate a digital terrain model and a digital surface model, which were further employed in calculation of a canopy height model (CHM). The CHM was used to estimate tree height using low pass and local maximum filters, and crown diameter was estimated based on an inverse watershed segmentation algorithm. UAV-based tree height and crown diameter estimates were validated against field measurements and resulted in 3.22 m (10.1%) and 0.81 m (7.02%) root mean square errors, respectively. The results showed high agreement between our estimates and field measurements, with an R² of 0.808 for tree height and an R² of 0.923 for crown diameter. Generally, the accuracy of the results was considered acceptable and confirmed the usefulness of this approach for estimating tree heights and crown diameter.

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

Forest canopy cover (FCC) is one of the most important forest inventory parameters and plays a critical role in evaluating forest functions. This study examines the potential of integrating Sentinel-1 (S-1) and Sentinel-2 (S-2) data to map FCC in the heterogeneous Mediterranean oak forests of western Iran in different data densities (one-year datasets vs. three-year datasets). This study used very high-resolution satellite images from Google Earth, gridded points, and field inventory plots to generate a reference dataset. Based on it, four FCC classes were defined, namely non-forest, sparse forest (FCC = 1–30%), medium-density forest (FCC = 31–60%), and dense forest (FCC > 60%). In this study, three machine learning (ML) models, including Random Forest (RF), Support Vector Machine (SVM), and Classification and Regression Tree (CART), were used in the Google Earth Engine and their performance was compared for classification. Results showed that the SVM produced the highest accuracy on FCC mapping. The three-year time series increased the ability of all ML models to classify FCC classes, in particular the sparse forest class, which was not distinguished well by the one-year dataset. Class-level accuracy assessment results showed a remarkable increase in F-1 scores for sparse forest classification by integrating S-1 and S-2 (10.4% to 18.2% increased for the CART and SVM ML models, respectively). In conclusion, the synergetic use of S-1 and S-2 spectral temporal metrics improved the classification accuracy compared to that obtained using only S-2. The study relied on open data and freely available tools and can be integrated into national monitoring systems of FCC in Mediterranean oak forests of Iran and neighboring countries with similar forest attributes.