Google Earth Engine and Artificial Intelligence (AI): A Comprehensive Review

Remote-sensing monitoring of colored dissolved organic matter in the Arctic Ocean

In the Arctic Ocean, variations in the colored dissolved organic matter (CDOM) have important value and significance. This study proposed and evaluated a novel method by combining the Google Earth Engine with a multilayer back-propagation neural network to retrieve CDOM concentration. This model performed well on the testing data and independent validation data (R2 = 0.76, RMSE = 0.37 m-1, MAPD = 35.43 %), and it was applied to Moderate Resolution Imaging Spectroradiometer (MODIS) images. The CDOM distribution in the Arctic Ocean and its main sea areas was first depicted during the ice-free period from 2002 to 2021, with average CDOM concentration in the range of 0.25 and 0.31 m-1. High CDOM concentration appeared in coastal areas affected by rivers on the Siberian side. The CDOM concentration was highly correlated with salinity (r = -0.92) and discharge (r > 0.68), while melting sea ice diluted seawater and CDOM concentration.

A 10-m national-scale map of ground-mounted photovoltaic power stations in China of 2020

We provide a remote sensing derived dataset for large-scale ground-mounted photovoltaic (PV) power stations in China of 2020, which has high spatial resolution of 10 meters. The dataset is based on the Google Earth Engine (GEE) cloud computing platform via random forest classifier and active learning strategy. Specifically, ground samples are carefully collected across China via both field survey and visual interpretation. Afterwards, spectral and texture features are calculated from publicly available Sentinel-2 imagery. Meanwhile, topographic features consisting of slope and aspect that are sensitive to PV locations are also included, aiming to construct a multi-dimensional and discriminative feature space. Finally, the trained random forest model is adopted to predict PV power stations of China parallelly on GEE. Technical validation has been carefully performed across China which achieved a satisfactory accuracy over 89%. Above all, as the first publicly released 10-m national-scale distribution dataset of China's ground-mounted PV power stations, it can provide data references for relevant researchers in fields such as energy, land, remote sensing and environmental sciences.

The 10-m cotton maps in Xinjiang, China during 2018-2021

Cotton maps (10 m) of Xinjiang (XJ_COTTON10), which is the largest cotton production region of China, were produced from 2018 to 2021 through supervised classification. A two-step mapping strategy, i.e., cropland mapping followed by cotton extraction, was employed to improve the accuracy and efficiency of cotton mapping for a large region of about 1.66 million km2 with high heterogeneity. Additionally, the time-series satellite data related to spectral, textural, structural, and phenological features were combined and used in a supervised random forest classifier. The cotton/non-cotton classification model achieved overall accuracies of about 95% and 90% on the test samples of the same and adjacent years, respectively. The proposed two-step cotton mapping strategy proved promising and effective in producing multi-year and consistent cotton maps. XJ_COTTON10 agreed well with the statistical areas of cotton at the county level (R2 = 0.84-0.94). This is the first cotton mapping for the entire Xinjiang at 10-meter resolution, which can provide a basis for high-precision cotton monitoring and policymaking in China.

Detecting and distinguishing between apicultural plants using UAV multispectral imaging

Detecting and distinguishing apicultural plants are important elements of the evaluation and quantification of potential honey production worldwide. Today, remote sensing can provide accurate plant distribution maps using rapid and efficient techniques. In the present study, a five-band multispectral unmanned aerial vehicle (UAV) was used in an established beekeeping area on Lemnos Island, Greece, for the collection of high-resolution images from three areas where Thymus capitatus and Sarcopoterium spinosum are present. Orthophotos of UAV bands for each area were used in combination with vegetation indices in the Google Earth Engine (GEE) platform, to classify the area occupied by the two plant species. From the five classifiers (Random Forest, RF; Gradient Tree Boost, GTB; Classification and Regression Trees, CART; Mahalanobis Minimum Distance, MMD; Support Vector Machine, SVM) in GEE, the RF gave the highest overall accuracy with a Kappa coefficient reaching 93.6%, 98.3%, 94.7%, and coefficient of 0.90, 0.97, 0.92 respectively for each case study. The training method used in the present study detected and distinguish the two plants with great accuracy and results were confirmed using 70% of the total score to train the GEE and 30% to assess the method's accuracy. Based on this study, identification and mapping of Thymus capitatus areas is possible and could help in the promotion and protection of this valuable species which, on many Greek Islands, is the sole foraging plant of honeybees.