The type of algorithm employed to classify remote sensing imageries plays a great role in affecting the accuracy. In recent decades, machine learning (ML) has received great attention due to its robustness in remote sensing image classification. In this regard, random forest (RF) and support vector machine (SVM) are two of the most widely used ML algorithms to generate land cover (LC) maps from satellite imageries. Although several comparisons have been conducted between these two algorithms, the findings are contradicting. Moreover, the comparisons were made on local-scale LC map generation either from high or medium resolution images using various software, but not Python. In this paper, we compared the performance of these two algorithms for large area LC mapping of parts of Africa using coarse resolution imageries in the Python platform by the employing Scikit-Learn (sklearn) library. We employed a big dataset, 297 metrics, comprised of systematically selected 9-month composite FegnYun-3C (FY-3C) satellite images with 1 km resolution. Several experiments were performed using a range of values to determine the best values for the two most important parameters of each classifier, the number of trees and the number of variables, for RF, and penalty value and gamma for SVM, and to obtain the best model of each algorithm. Our results showed that RF outperformed SVM yielding 0.86 (OA) and 0.83 (k), which are 1–2% and 3% higher than the best SVM model, respectively. In addition, RF performed better in mixed class classification; however, it performed almost the same when classifying relatively pure classes with distinct spectral variation, i.e., consisting of less mixed pixels. Furthermore, RF is more efficient in handling large input datasets where the SVM fails. Hence, RF is a more robust ML algorithm especially for heterogeneous large area mapping using coarse resolution images. Finally, default parameter values in the sklearn library work well for satellite image classification with minor/or no adjustment for these algorithms.

The accurate estimation of forest above-ground biomass (AGB) is crucial for sustainable forest management and tracking the carbon cycle of forest ecosystem. Machine learning algorithms have been proven to have great potential in forest AGB estimation with remote sensing data. Though many studies have demonstrated that a single machine learning model can produce highly accurate estimations of forest AGB in many situations, efforts are still required to explore the possible improvement in forest AGB estimation for a specific scenario under study. This study aims to investigate the performance of novel ensemble machine learning methods for forest AGB estimation and analyzes whether these methods are affected by forest types, independent variables, and spatial autocorrelation. Four well-known machine learning models (CatBoost, LightGBM, random forest (RF), and XGBoost) were compared for forest AGB estimation in the study using eight scenarios devised on the basis of two study regions, two variable types, and two validation strategies. Subsequently, a hybrid model combining the strengths of these individual models was proposed for forest AGB estimation. The findings indicated that no individual model outperforms the others in all scenarios. The RF model demonstrates superior performance in scenarios 5, 6, and 7, while the CatBoost model shows the best performance in the remaining scenarios. Moreover, the proposed hybrid model consistently has the best performance in all scenarios in spite of some uncertainties. The ensemble strategy developed in this study for the hybrid model substantially improves estimation accuracy and exhibits greater stability, effectively addressing the challenge of model selection encountered in the forest AGB forecasting process.

The selection and representation of remote sensing image classification features play crucial roles in image classification accuracy. To effectively improve the classification accuracy of features, an improved U-Net network framework based on multi-feature fusion perception is proposed in this paper. This framework adds the channel attention module (CAM-UNet) to the original U-Net framework and cascades the shallow features with the deep semantic features, replaces the classification layer in the original U-Net network with a support vector machine, and finally uses the majority voting game theory algorithm to fuse the multifeature classification results and obtain the final classification results. This study used the forest distribution in Xingbin District, Laibin City, Guangxi Zhuang Autonomous Region as the research object, which is based on Landsat 8 multispectral remote sensing images, and, by combining spectral features, spatial features, and advanced semantic features, overcame the influence of the reduction in spatial resolution that occurs with the deepening of the network on the classification results. The experimental results showed that the improved algorithm can improve classification accuracy. Before the improvement, the overall segmentation accuracy and segmentation accuracy of the forestland increased from 90.50% to 92.82% and from 95.66% to 97.16%, respectively. The forest cover results obtained by the algorithm proposed in this paper can be used as input data for regional ecological models, which is conducive to the development of accurate and real-time vegetation growth change models.

The selection and representation of classification features in remote sensing image play crucial roles in image classification accuracy. To effectively improve the features classification accuracy, an improved U-Net remote sensing classification algorithm fusing attention and multiscale features is proposed in this paper, called spatial attention-atrous spatial pyramid pooling U-Net (SA-UNet). This framework connects atrous spatial pyramid pooling (ASPP) with the convolutional units of the encoder of the original U-Net in the form of residuals. The ASPP module expands the receptive field, integrates multiscale features in the network, and enhances the ability to express shallow features. Through the fusion residual module, shallow and deep features are deeply fused, and the characteristics of shallow and deep features are further used. The spatial attention mechanism is used to combine spatial with semantic information so that the decoder can recover more spatial information. In this study, the crop distribution in central Guangxi province was analyzed, and experiments were conducted based on Landsat 8 multispectral remote sensing images. The experimental results showed that the improved algorithm increases the classification accuracy, with the accuracy increasing from 93.33% to 96.25%, The segmentation accuracy of sugarcane, rice, and other land increased from 96.42%, 63.37%, and 88.43% to 98.01%, 83.21%, and 95.71%, respectively. The agricultural planting area results obtained by the proposed algorithm can be used as input data for regional ecological models, which is conducive to the development of accurate and real-time crop growth change models.

Crop type classification with satellite imageries is widely applied in support of crop production management and food security strategy. The abundant supply of these satellite data is accelerating and blooming the application of crop classification as satellite data at 10 m to 30 m spatial resolution have been made accessible easily, widely and free of charge, including optical sensors, the wide field of viewer (WFV) onboard the GaoFen (GF, high resolution in English) series from China, the MultiSpectral Instrument (MSI) onboard Sentinel 2 (S2) from Europe and the Operational Land Imager (OLI) onboard Landsat 8 (L8) from USA, thanks to the implementation of the open data policy. There are more options in using the satellite data as these three data sources are available. This paper explored the different capability of these three data sources for the crop type mapping in the same area and within the same growing season. The study was executed in a flat and irrigated area in Northwest China. Nine types of crop were classified using these three kinds of time series of data sources in 2017 and 2018, respectively. The same suites of the training samples and validation samples were applied for each of the data sources. Random Forest (RF) was used as the classifier for the crop type classification. The confusion error matrix with the OA, Kappa and F1-score was used to evaluate the accuracy of the classifications. The result shows that GF-1 relatively has the lowest accuracy as a consequence of the limited spectral bands, but the accuracy is at 93–94%, which is still excellent and acceptable for crop type classification. S2 achieved the highest accuracy of 96–98%, with 10 available bands for the crop type classification at either 10 m or 20 m. The accuracy of 97–98% for L8 is in the middle but the difference is small in comparison with S2. Any of these satellite data may be used for the crop type classification within the growing season, with a very good accuracy if the training datasets were well tuned.

The atmosphere has substantial effects on optical remote sensing imagery of the Earth’s surface from space. These effects come through the functioning of atmospheric particles on the radiometric transfer from the Earth’s surface through the atmosphere to the sensor in space. Precipitable water vapor (PWV), CO₂, ozone, and aerosol in the atmosphere are very important among the particles through their functioning. This study presented an algorithm to retrieve total PWV from the Chinese second-generation polar-orbiting meteorological satellite FengYun 3D Medium Resolution Spectral Imager 2 (FY-3D MERSI-2) data, which have three near-infrared (NIR) water vapor absorbing channels, i.e., channel 16, 17, and 18. The algorithm was improved from the radiance ratio technique initially developed for Moderate-Resolution Imaging Spectroradiometer (MODIS) data. MODTRAN 5 was used to simulate the process of radiant transfer from the ground surfaces to the sensor at various atmospheric conditions for estimation of the coefficients of ratio technique, which was achieved through statistical regression analysis between the simulated radiance and transmittance values for FY-3D MERSI-2 NIR channels. The algorithm was then constructed as a linear combination of the three-water vapor absorbing channels of FY-3D MERSI-2. Measurements from two ground-based reference datasets were used to validate the algorithm: the sun photometer measurements of Aerosol Robotic Network (AERONET) and the microwave radiometer measurements of Energy’s Atmospheric Radiation Measurement Program (ARMP). The validation results showed that the algorithm performs very well when compared with the ground-based reference datasets. The estimated PWV values come with root mean square error (RMSE) of 0.28 g/cm² for the ARMP and 0.26 g/cm² for the AERONET datasets, with bias of 0.072 g/cm² and 0.096 g/cm² for the two reference datasets, respectively. The accuracy of the proposed algorithm revealed a better consistency with ground-based reference datasets. Thus, the proposed algorithm could be used as an alternative to retrieve PWV from FY-3D MERSI-2 data for various remote sensing applications such as agricultural monitoring, climate change, hydrologic cycle, and so on at various regional and global scales.