The production of land cover maps through satellite image classification is a frequent task in remote sensing. Random Forest (RF) and Support Vector Machine (SVM) are the two most well-known and recurrently used methods for this task. In this paper, we evaluate the pros and cons of using an RF-based kernel (RFK) in an SVM compared to using the conventional Radial Basis Function (RBF) kernel and standard RF classifier. A time series of seven multispectral WorldView-2 images acquired over Sukumba (Mali) and a single hyperspectral AVIRIS image acquired over Salinas Valley (CA, USA) are used to illustrate the analyses. For each study area, SVM-RFK, RF, and SVM-RBF were trained and tested under different conditions over ten subsets. The spectral features for Sukumba were extended by obtaining vegetation indices (VIs) and grey-level co-occurrence matrices (GLCMs), the Salinas dataset is used as benchmarking with its original number of features. In Sukumba, the overall accuracies (OAs) based on the spectral features only are of 81.34 % , 81.08 % and 82.08 % for SVM-RFK, RF, and SVM-RBF. Adding VI and GLCM features results in OAs of 82 % , 80.82 % and 77.96 % . In Salinas, OAs are of 94.42 % , 95.83 % and 94.16 % . These results show that SVM-RFK yields slightly higher OAs than RF in high dimensional and noisy experiments, and it provides competitive results in the rest of the experiments. They also show that SVM-RFK generates highly competitive results when compared to SVM-RBF while substantially reducing the time and computational cost associated with parametrizing the kernel. Moreover, SVM-RFK outperforms SVM-RBF in high dimensional and noisy problems. RF was also used to select the most important features for the extended dataset of Sukumba; the SVM-RFK derived from these features improved the OA of the previous SVM-RFK by 2%. Thus, the proposed SVM-RFK classifier is as at least as good as RF and SVM-RBF and can achieve considerable improvements when applied to high dimensional data and when combined with RF-based feature selection methods.

The use of deep learning (DL) approaches for the analysis of remote sensing (RS) data is rapidly increasing. DL techniques have provided excellent results in applications ranging from parameter estimation to image classification and anomaly detection. Although the vast majority of studies report precision indicators, there is a lack of studies dealing with the interpretability of the predictions. This shortcoming hampers a wider adoption of DL approaches by a wider users community, as model’s decisions are not accountable. In applications that involve the management of public budgets or policy compliance, a better interpretability of predictions is strictly required. This work aims to deepen the understanding of a recurrent neural network for land use classification based on Sentinel-2 time series in the context of the European Common Agricultural Policy (CAP). This permits to address the relevance of predictors in the classification process leading to an improved understanding of the behaviour of the network. The conducted analysis demonstrates that the red and near infrared Sentinel-2 bands convey the most useful information. With respect to the temporal information, the features derived from summer acquisitions were the most influential. These results contribute to the understanding of models used for decision making in the CAP to accomplish the European Green Deal (EGD) designed in order to counteract climate change, to protect biodiversity and ecosystems, and to ensure a fair economic return for farmers.

This paper reviews the most important information fusion data-driven algorithms based on Machine Learning (ML) techniques for problems in Earth observation. Nowadays we observe and model the Earth with a wealth of observations, from a plethora of different sensors, measuring states, fluxes, processes and variables, at unprecedented spatial and temporal resolutions. Earth observation is well equipped with remote sensing systems, mounted on satellites and airborne platforms, but it also involves in-situ observations, numerical models and social media data streams, among other data sources. Data-driven approaches, and ML techniques in particular, are the natural choice to extract significant information from this data deluge. This paper produces a thorough review of the latest work on information fusion for Earth observation, with a practical intention, not only focusing on describing the most relevant previous works in the field, but also the most important Earth observation applications where ML information fusion has obtained significant results. We also review some of the most currently used data sets, models and sources for Earth observation problems, describing their importance and how to obtain the data whether needed. Finally, we illustrate the application of ML data fusion with a representative set of case studies, as well as we discuss and outlook the near future of the field.

Smallholder farmers cultivate more than 80% of the cropland area available in Africa. The intrinsic characteristics of such farms include complex crop-planting patterns, and small fields that are vaguely delineated. These characteristics pose challenges to mapping crops and fields from space. In this study, we evaluate the use of a cloud-based multi-temporal ensemble classifier to map smallholder farming systems in a case study for southern Mali. The ensemble combines a selection of spatial and spectral features derived from multi-spectral Worldview-2 images, field data, and five machine learning classifiers to produce a map of the most prevalent crops in our study area. Different ensemble sizes were evaluated using two combination rules, namely majority voting and weighted majority voting. Both strategies outperform any of the tested single classifiers. The ensemble based on the weighted majority voting strategy obtained the higher overall accuracy (75.9%). This means an accuracy improvement of 4.65% in comparison with the average overall accuracy of the best individual classifier tested in this study. The maximum ensemble accuracy is reached with 75 classifiers in the ensemble. This indicates that the addition of more classifiers does not help to continuously improve classification results. Our results demonstrate the potential of ensemble classifiers to map crops grown by West African smallholders. The use of ensembles demands high computational capability, but the increasing availability of cloud computing solutions allows their efficient implementation and even opens the door to the data processing needs of local organizations.

A large number of studies have been published addressing sugarcane management and monitoring to increase productivity and production as well as to better understand landscape dynamics and environmental threats. Building on existing reviews which mainly focused on the crop’s spectral behavior, a comprehensive review is provided which considers the progress made using novel data analysis techniques and improved data sources. To complement the available reviews, and to make the large body of research more easily accessible for both researchers and practitioners, in this review (i) we summarized remote sensing applications from 1981 to 2020, (ii) discussed key strengths and weaknesses of remote sensing approaches in the sugarcane context, and (iii) described the challenges and opportunities for future earth observation (EO)-based sugarcane monitoring and management. More than one hundred scientific studies were assessed regarding sugarcane mapping (52 papers), crop growth anomaly detection (11 papers), health monitoring (14 papers), and yield estimation (30 papers). The articles demonstrate that decametric satellite sensors such as Landsat and Sentinel-2 enable a reliable, cost-efficient, and timely mapping and monitoring of sugarcane by overcoming the ground sampling distance (GSD)-related limitations of coarser hectometric resolution data, while offering rich spectral information in the frequently recorded data. The Sentinel-2 constellation in particular provides fine spatial resolution at 10 m and high revisit frequency to support sugarcane management and other applications over large areas. For very small areas, and in particular for up-scaling and calibration purposes, unmanned aerial vehicles (UAV) are also useful. Multi-temporal and multi-source data, together with powerful machine learning approaches such as the random forest (RF) algorithm, are key to providing efficient monitoring and mapping of sugarcane growth, health, and yield. A number of difficulties for sugarcane monitoring and mapping were identified that are also well known for other crops. Those difficulties relate mainly to the often (i) time consuming pre-processing of optical time series to cope with atmospheric perturbations and cloud coverage, (ii) the still important lack of analysis-ready-data (ARD), (iii) the diversity of environmental and growth conditions—even for a given country—under which sugarcane is grown, superimposing non-crop related radiometric information on the observed sugarcane crop, and (iv) the general ill-posedness of retrieval and classification approaches which adds ambiguity to the derived information.

Remote sensing optical sensors onboard operational satellites cannot have high spectral, spatial and temporal resolutions simultaneously. In addition, clouds and aerosols can adversely affect the signal contaminating the land surface observations. We present a HIghly Scalable Temporal Adaptive Reflectance Fusion Model (HISTARFM) algorithm to combine multispectral images of different sensors to reduce noise and produce monthly gap free high resolution (30 m) observations over land. Our approach uses images from the Landsat (30 m spatial resolution and 16 day revisit cycle) and the MODIS missions, both from Terra and Aqua platforms (500 m spatial resolution and daily revisit cycle). We implement a bias-aware Kalman filter method in the Google Earth Engine (GEE) platform to obtain fused images at the Landsat spatial-resolution. The added bias correction in the Kalman filter estimates accounts for the fact that both model and observation errors are temporally auto-correlated and may have a non-zero mean. This approach also enables reliable estimation of the uncertainty associated with the final reflectance estimates, allowing for error propagation analyses in higher level remote sensing products. Quantitative and qualitative evaluations of the generated products through comparison with other state-of-the-art methods confirm the validity of the approach, and open the door to operational applications at enhanced spatio-temporal resolutions at broad continental scales.

No abstract

No abstract