Evaluating the Effectiveness of Machine Learning and Deep Learning Models Combined Time-Series Satellite Data for Multiple Crop Types Classification over a Large-Scale Region

Identification of Paddy Croplands and Its Stages Using Remote Sensors: A Systematic Review

Rice is a staple food that feeds nearly half of the world's population. With the population of our planet expected to keep growing, it is crucial to carry out accurate mapping, monitoring, and assessments since these could significantly impact food security, climate change, spatial planning, and land management. Using the PRISMA systematic review protocol, this article identified and selected 122 scientific articles (journals papers and conference proceedings) addressing different remote sensing-based methodologies to map paddy croplands, published between 2010 and October 2022. This analysis includes full coverage of the mapping of rice paddies and their various stages of crop maturity. This review paper classifies the methods based on the data source: (a) multispectral (62%), (b) multisource (20%), and (c) radar (18%). Furthermore, it analyses the impact of machine learning on those methodologies and the most common algorithms used. We found that MODIS (28%), Sentinel-2 (18%), Sentinel-1 (15%), and Landsat-8 (11%) were the most used sensors. The impact of Sentinel-1 on multisource solutions is also increasing due to the potential of backscatter information to determine textures in different stages and decrease cloud cover constraints. The preferred solutions include phenology algorithms via the use of vegetation indices, setting thresholds, or applying machine learning algorithms to classify images. In terms of machine learning algorithms, random forest is the most used (17 times), followed by support vector machine (12 times) and isodata (7 times). With the continuous development of technology and computing, it is expected that solutions such as multisource solutions will emerge more frequently and cover larger areas in different locations and at a higher resolution. In addition, the continuous improvement of cloud detection algorithms will positively impact multispectral solutions.

Superpixel segmentation integrated feature subset selection for wetland classification over Yellow River Delta

Wetlands are one of the world's most significant and vulnerable ecosystems. The wetlands of the Yellow River Delta are subject to multiple influences of ocean tidal action and the massive sediment deposits of the Yellow River, resulting in a more complex and unstable composition of land cover types. To better distinguish the wetlands in the region, we conducted the classification using an object-oriented combined with feature preference machine learning approach. To alleviate the pretzel phenomenon in pixel-based classification, a superpixel segmentation method using the watershed algorithm with H-minima labeling was used to segment the images at the optimal scale. The best feature subset for classification was filtered using the recursive feature elimination cross-validation approach, which extracts multiple spectral indices from the images. A random forest classifier combining superpixel segmentation and feature selection methods was proposed for the wetland classification. The model improves the classification accuracy of wetlands compared to three classical pixel-based machine learning classification methods. And the overall accuracy was 91.74% and the kappa coefficient was 0.9078, both of which were improved by about 4.53% and 0.0506, respectively, compared with the best-performing random forest classifier in pixel-oriented. The results showed that this method can effectively improve the classification accuracy of the Yellow River Delta wetlands compared with the previous studies.

CerealNet: A Hybrid Deep Learning Architecture for Cereal Crop Mapping Using Sentinel-2 Time-Series

Remote sensing-based crop mapping has continued to grow in economic importance over the last two decades. Given the ever-increasing rate of population growth and the implications of multiplying global food production, the necessity for timely, accurate, and reliable agricultural data is of the utmost importance. When it comes to ensuring high accuracy in crop maps, spectral similarities between crops represent serious limiting factors. Crops that display similar spectral responses are notorious for being nearly impossible to discriminate using classical multi-spectral imagery analysis. Chief among these crops are soft wheat, durum wheat, oats, and barley. In this paper, we propose a unique multi-input deep learning approach for cereal crop mapping, called “CerealNet”. Two time-series used as input, from the Sentinel-2 bands and NDVI (Normalized Difference Vegetation Index), were fed into separate branches of the LSTM-Conv1D (Long Short-Term Memory Convolutional Neural Networks) model to extract the temporal and spectral features necessary for the pixel-based crop mapping. The approach was evaluated using ground-truth data collected in the Gharb region (northwest of Morocco). We noted a categorical accuracy and an F1-score of 95% and 94%, respectively, with minimal confusion between the four cereal classes. CerealNet proved insensitive to sample size, as the least-represented crop, oats, had the highest F1-score. This model was compared with several state-of-the-art crop mapping classifiers and was found to outperform them. The modularity of CerealNet could possibly allow for injecting additional data such as Synthetic Aperture Radar (SAR) bands, especially when optical imagery is not available.

Introducing ARTMO's Machine-Learning Classification Algorithms Toolbox: Application to Plant-Type Detection in a Semi-Steppe Iranian Landscape

Accurate plant-type (PT) detection forms an important basis for sustainable land management maintaining biodiversity and ecosystem services. In this sense, Sentinel-2 satellite images of the Copernicus program offer spatial, spectral, temporal, and radiometric characteristics with great potential for mapping and monitoring PTs. In addition, the selection of a best-performing algorithm needs to be considered for obtaining PT classification as accurate as possible. To date, no freely downloadable toolbox exists that brings the diversity of the latest supervised machine-learning classification algorithms (MLCAs) together into a single intuitive user-friendly graphical user interface (GUI). To fill this gap and to facilitate and automate the usage of MLCAs, here we present a novel GUI software package that allows systematically training, validating, and applying pixel-based MLCA models to remote sensing imagery. The so-called MLCA toolbox has been integrated within ARTMO's software framework developed in Matlab which implements most of the state-of-the-art methods in the machine learning community. To demonstrate its utility, we chose a heterogeneous case study scene, a landscape in Southwest Iran to map PTs. In this area, four main PTs were identified, consisting of shrub land, grass land, semi-shrub land, and shrub land-grass land vegetation. Having developed 21 MLCAs using the same training and validation, datasets led to varying accuracy results. Gaussian process classifier (GPC) was validated as the top-performing classifier, with an overall accuracy (OA) of 90%. GPC follows a Laplace approximation to the Gaussian likelihood under the supervised classification framework, emerging as a very competitive alternative to common MLCAs. Random forests resulted in the second-best performance with an OA of 86%. Two other types of ensemble-learning algorithms, i.e., tree-ensemble learning (bagging) and decision tree (with error-correcting output codes), yielded an OA of 83% and 82%, respectively. Following, thirteen classifiers reported OA between 70% and 80%, and the remaining four classifiers reported an OA below 70%. We conclude that GPC substantially outperformed all classifiers, and thus, provides enormous potential for the classification of a diversity of land-cover types. In addition, its probabilistic formulation provides valuable band ranking information, as well as associated predictive variance at a pixel level. Nevertheless, as these are supervised (data-driven) classifiers, performances depend on the entered training data, meaning that an assessment of all MLCAs is crucial for any application. Our analysis demonstrated the efficacy of ARTMO's MLCA toolbox for an automated evaluation of the classifiers and subsequent thematic mapping.

Cyclic Gate Recurrent Neural Networks for Time Series Data with Missing Values

Gated Recurrent Neural Networks (RNNs) such as LSTM and GRU have been highly effective in handling sequential time series data in recent years. Although Gated RNNs have an inherent ability to learn complex temporal dynamics, there is potential for further enhancement by enabling these deep learning networks to directly use time information to recognise time-dependent patterns in data and identify important segments of time. Synonymous with time series data in real-world applications are missing values, which often reduce a model’s ability to perform predictive tasks. Historically, missing values have been handled by simple or complex imputation techniques as well as machine learning models, which manage the missing values in the prediction layers. However, these methods do not attempt to identify the significance of data segments and therefore are susceptible to poor imputation values or model degradation from high missing value rates. This paper develops Cyclic Gate enhanced recurrent neural networks with learnt waveform parameters to automatically identify important data segments within a time series and neglect unimportant segments. By using the proposed networks, the negative impact of missing data on model performance is mitigated through the addition of customised cyclic opening and closing gate operations. Cyclic Gate Recurrent Neural Networks are tested on several sequential time series datasets for classification performance. For long sequence datasets with high rates of missing values, Cyclic Gate enhanced RNN models achieve higher performance metrics than standard gated recurrent neural network models, conventional non-neural network machine learning algorithms and current state of the art RNN cell variants.

Crop Identification Based on Multi-Temporal Active and Passive Remote Sensing Images

Although vegetation index time series from optical images are widely used for crop mapping, it remains difficult to obtain sufficient time-series data because of satellite revisit time and weather in some areas. To address this situation, this paper considered Wen County, Henan Province, Central China as the research area and fused multi-source features such as backscatter coefficient, vegetation index, and time series based on Sentinel-1 and -2 data to identify crops. Through comparative experiments, this paper studied the feasibility of identifying crops with multi-temporal data and fused data. The results showed that the accuracy of multi-temporal Sentinel-2 data increased by 9.2% compared with single-temporal Sentinel-2 data, and the accuracy of multi-temporal fusion data improved by 17.1% and 2.9%, respectively, compared with multi-temporal Sentinel-1 and Sentinel-2 data. Multi-temporal data well-characterizes the phenological stages of crop growth, thereby improving the classification accuracy. The fusion of Sentinel-1 synthetic aperture radar data and Sentinel-2 optical data provide sufficient time-series data for crop identification. This research can provide a reference for crop recognition in precision agriculture.