Integration of Optical and Synthetic Aperture Radar Imagery for Improving Crop Mapping in Northwestern Benin, West Africa

Use of Optical and Radar Imagery for Crop Type Classification in Africa: A Review

Multi-source remote sensing-derived information on crops contributes significantly to agricultural monitoring, assessment, and management. In Africa, some challenges (i.e., small-scale farming practices associated with diverse crop types and agricultural system complexity, and cloud coverage during the growing season) can imped agricultural monitoring using multi-source remote sensing. The combination of optical remote sensing and synthetic aperture radar (SAR) data has emerged as an opportune strategy for improving the precision and reliability of crop type mapping and monitoring. This work aims to conduct an extensive review of the challenges of agricultural monitoring and mapping in Africa in great detail as well as the current research progress of agricultural monitoring based on optical and Radar satellites. In this context optical data may provide high spatial resolution and detailed spectral information, which allows for the differentiation of different crop types based on their spectral signatures. However, synthetic aperture radar (SAR) satellites can provide important contributions given the ability of this technology to penetrate cloud cover, particularly in African tropical regions, as opposed to optical data. This review explores various combination techniques employed to integrate optical and SAR data for crop type classification and their applicability and limitations in the context of African countries. Furthermore, challenges are discussed in this review as well as and the limitations associated with optical and SAR data combination, such as the data availability, sensor compatibility, and the need for accurate ground truth data for model training and validation. This study also highlights the potential of advanced modelling (i.e., machine learning algorithms, such as support vector machines, random forests, and convolutional neural networks) in improving the accuracy and automation of crop type classification using combined data. Finally, this review concludes with future research directions and recommendations for utilizing optical and SAR data combination techniques in crop type classification for African agricultural systems. Furthermore, it emphasizes the importance of developing robust and scalable classification models that can accommodate the diversity of crop types, farming practices, and environmental conditions prevalent in Africa. Through the utilization of combined remote sensing technologies, informed decisions can be made to support sustainable agricultural practices, strengthen nutritional security, and contribute to the socioeconomic development of the continent.

The governance of community gardens as commons and its role in the socio-ecological outcomes of gardening in Austin, Texas, USA

Community gardens represent vacant lots in urban areas with public or private land ownership that community members use primarily for urban agriculture. This research studies community gardens in Austin, Texas (USA), with the focus on: (1) approaches taken to govern community gardens and (2) socio-ecological outcomes of gardening associated with the implemented models of governance. Social outcomes are represented by the level of gardeners' satisfaction and perceptions of their success. Environmental outcomes represent ecological services provided by gardens as green spaces and expressed through net primary productivity (NPP), which measures carbon sequestration. This paper argues that these types of outcomes in community gardens are codependent and affect each other, and the governance approach determines what forms this interdependence takes. This study employs Ostrom's socio-ecological systems (SES) framework that reflects both social and natural aspects of community gardening and explains the connection between the governance approaches, gardeners' perception of their success, and changes in carbon sequestration. This paper uses a mixed-methods approach with key informant interviews with managers of community gardens yielding both qualitative and quantitative data. Remote sensing analysis is applied to calculate the amount of biomass for the carbon sequestration model using remote sensing imagery from the ECOsystem Spaceborne Thermal Radiometer Experiment on Space Station (ECOSTRESS) and Planet Inc. The analysis reveals that the highest measurements of the social and ecological performance in community gardens in Austin are associated with 'bottom-up' governance structures where community members are in charge of decision-making and management.

Research on remote sensing classification of fruit trees based on Sentinel-2 multi-temporal imageries

Accurately obtaining the spatial distribution information of fruit tree planting is of great significance to the development of fruit tree growth monitoring, disease and pest control, and yield estimation. In this study, the Sentenel-2 multispectral remote sensing imageries of different months during the growth period of the fruit trees were used as the data source, and single month vegetation indices, accumulated monthly vegetation indices (∑VIs), and difference vegetation indices between adjacent months (∆VIs) were constructed as input variables. Four conventional vegetation indices of NDVI, PSRI, GNDVI, and RVI and four improved vegetation indices of NDVIre1, NDVIre2, NDVIre3, and NDVIre4 based on the red-edge band were selected to construct a decision tree classification model combined with machine learning technology. Through the analysis of vegetation indices under different treatments and different months, combined with the attribute of Feature_importances_, the vegetation indices of different periods with high contribution were selected as input features, and the Max_depth values of the decision tree model were determined by the hyperparameter learning curve. The results have shown that when the Max_depth value of the decision tree model of the vegetation indices under the three treatments was 6, 8, and 8, the model classification was the best. The accuracy of the three vegetation index processing models on the training set were 0.8936, 0.9153, and 0.8887, and the accuracy on the test set were 0.8355, 0.7611, and 0.7940, respectively. This method could be applied to remote sensing classification of fruit trees in a large area, and could provide effective technical means for monitoring fruit tree planting areas with medium and high resolution remote sensing imageries.

Performance and the Optimal Integration of Sentinel-1/2 Time-Series Features for Crop Classification in Northern Mongolia

Accurate and early crop-type maps are essential for agricultural policy development and food production assessment at regional and national levels. This study aims to produce a crop-type map with acceptable accuracy and spatial resolution in northern Mongolia by optimizing the combination of Sentinel-1 (S1) and Sentinel-2 (S2) images with the Google Earth Engine (GEE) environment. A total of three satellite data combination scenarios are set, including S1 alone, S2 alone, and the combination of S1 and S2. In order to avoid the impact of data gaps caused by clouds on crop classification, this study reconstructed the time series of S1 and S2 with a 10-day interval using the median composite method, linear moving interpolation, and Savitzky–Golay (SG) filter. Our results indicated that crop-type classification accuracy increased with the increase in data length to all three data combination scenarios. S2 alone has higher accuracy than S1 alone and the combination of S1 and S2. The crop-type map with the highest accuracy was generated using S2 data from 150 days of the year (DOY) (11 May) to 260 DOY (18 September). The OA and kappa were 0.93 and 0.78, respectively, and the F1-score for spring wheat and rapeseed were 0.96 and 0.80, respectively. The classification accuracy of the crop increased rapidly from 210 DOY (end of July) to 260 DOY (August to mid-September), and then it remained stable after 260 DOY. Based on our analysis, we filled the gap of the crop-type map with 10 m spatial resolution in northern Mongolia, revealing the best satellite combination and the best period for crop-type classification, which can benefit the achievement of sustainable development goals 2 (SDGs2).

Spatial Transferability of Random Forest Models for Crop Type Classification Using Sentinel-1 and Sentinel-2

Large-scale crop type mapping often requires prediction beyond the environmental settings of the training sites. Shifts in crop phenology, field characteristics, or ecological site conditions in the previously unseen area, may reduce the classification performance of machine learning classifiers that often overfit to the training sites. This study aims to assess the spatial transferability of Random Forest models for crop type classification across Germany. The effects of different input datasets, i.e., only optical, only Synthetic Aperture Radar (SAR), and optical-SAR data combination, and the impact of spatial feature selection were systematically tested to identify the optimal approach that shows the highest accuracy in the transfer region. The spatial feature selection, a feature selection approach combined with spatial cross-validation, should remove features that carry site-specific information in the training data, which in turn can reduce the accuracy of the classification model in previously unseen areas. Seven study sites distributed over Germany were analyzed using reference data for the major 11 crops grown in the year 2018. Sentinel-1 and Sentinel-2 data from October 2017 to October 2018 were used as input. The accuracy estimation was performed using the spatially independent sample sets. The results of the optical-SAR combination outperformed those of single sensors in the training sites (maximum F1-score–0.85), and likewise in the areas not covered by training data (maximum F1-score–0.79). Random forest models based on only SAR features showed the lowest accuracy losses when transferred to unseen regions (average F1loss–0.04). In contrast to using the entire feature set, spatial feature selection substantially reduces the number of input features while preserving good predictive performance on unseen sites. Altogether, applying spatial feature selection to a combination of optical-SAR features or using SAR-only features is beneficial for large-scale crop type classification where training data is not evenly distributed over the complete study region.

Data Fusion in Agriculture: Resolving Ambiguities and Closing Data Gaps

Acquiring useful data from agricultural areas has always been somewhat of a challenge, as these are often expansive, remote, and vulnerable to weather events. Despite these challenges, as technologies evolve and prices drop, a surge of new data are being collected. Although a wealth of data are being collected at different scales (i.e., proximal, aerial, satellite, ancillary data), this has been geographically unequal, causing certain areas to be virtually devoid of useful data to help face their specific challenges. However, even in areas with available resources and good infrastructure, data and knowledge gaps are still prevalent, because agricultural environments are mostly uncontrolled and there are vast numbers of factors that need to be taken into account and properly measured for a full characterization of a given area. As a result, data from a single sensor type are frequently unable to provide unambiguous answers, even with very effective algorithms, and even if the problem at hand is well defined and limited in scope. Fusing the information contained in different sensors and in data from different types is one possible solution that has been explored for some decades. The idea behind data fusion involves exploring complementarities and synergies of different kinds of data in order to extract more reliable and useful information about the areas being analyzed. While some success has been achieved, there are still many challenges that prevent a more widespread adoption of this type of approach. This is particularly true for the highly complex environments found in agricultural areas. In this article, we provide a comprehensive overview on the data fusion applied to agricultural problems; we present the main successes, highlight the main challenges that remain, and suggest possible directions for future research.

Identification of Crop Type Based on C-AENN Using Time Series Sentinel-1A SAR Data

Crop type identification is the initial stage and an important part of the agricultural monitoring system. It is well known that synthetic aperture radar (SAR) Sentinel-1A imagery provides a reliable data source for crop type identification. However, a single-temporal SAR image does not contain enough features, and the unique physical characteristics of radar images are relatively lacking, which limits its potential in crop mapping. In addition, current methods may not be applicable for time -series SAR data. To address the above issues, a new crop type identification method was proposed. Specifically, a farmland mask was firstly generated by the object Markov random field (OMRF) model to remove the interference of non-farmland factors. Then, the features of the standard backscatter coefficient, Sigma-naught (σ0), and the normalized backscatter coefficient by the incident angle, Gamma-naught (γ0), were extracted for each type of crop, and the optimal feature combination was found from time -series SAR images by means of Jeffries-Matusita (J-M) distance analysis. Finally, to make efficient utilization of optimal multi-temporal feature combination, a new network, the convolutional-autoencoder neural network (C-AENN), was developed for the crop type identification task. In order to prove the effectiveness of the method, several classical machine learning methods such as support vector machine (SVM), random forest (RF), etc., and deep learning methods such as one dimensional convolutional neural network (1D-CNN) and stacked auto-encoder (SAE), etc., were used for comparison. In terms of quantitative assessment, the proposed method achieved the highest accuracy, with a macro-F1 score of 0.9825, an overall accuracy (OA) score of 0.9794, and a Kappa coefficient (Kappa) score of 0.9705. In terms of qualitative assessment, four typical regions were chosen for intuitive comparison with the sample maps, and the identification result covering the study area was compared with a contemporaneous optical image, which indicated the high accuracy of the proposed method. In short, this study enables the effective identification of crop types, which demonstrates the importance of multi-temporal radar images in feature combination and the necessity of deep learning networks to extract complex features.

An Interannual Transfer Learning Approach for Crop Classification in the Hetao Irrigation District, China

Crop type classification is critical for crop production estimation and optimal water allocation. Crop type data are challenging to generate if crop reference data are lacking, especially for target years with reference data missed in collection. Is it possible to transfer a trained crop type classification model to retrace the historical spatial distribution of crop types? Taking the Hetao Irrigation District (HID) in China as the study area, this study first designed a 10 m crop type classification framework based on the Google Earth Engine (GEE) for crop type mapping in the current season. Then, its interannual transferability to accurately retrace historical crop distributions was tested. The framework used Sentinel-1/2 data as the satellite data source, combined percentile, and monthly composite approaches to generate classification metrics and employed a random forest classifier with 300 trees for crop classification. Based on the proposed framework, this study first developed a 10 m crop type map of the HID for 2020 with an overall accuracy (OA) of 0.89 and then obtained a 10 m crop type map of the HID for 2019 with an OA of 0.92 by transferring the trained model for 2020 without crop reference samples. The results indicated that the designed framework could effectively identify HID crop types and have good transferability to obtain historical crop type data with acceptable accuracy. Our results found that SWIR1, Green, and Red Edge2 were the top three reflectance bands for crop classification. The land surface water index (LSWI), normalized difference water index (NDWI), and enhanced vegetation index (EVI) were the top three vegetation indices for crop classification. April to August was the most suitable time window for crop type classification in the HID. Sentinel-1 information played a positive role in the interannual transfer of the trained model, increasing the OA from 90.73% with Sentinel 2 alone to 91.58% with Sentinel-1 and Sentinel-2 together.

High Resolution, Annual Maps of Field Boundaries for Smallholder-Dominated Croplands at National Scales

Mapping the characteristics of Africa’s smallholder-dominated croplands, including the sizes and numbers of fields, can provide critical insights into food security and a range of other socioeconomic and environmental concerns. However, accurately mapping these systems is difficult because there is 1) a spatial and temporal mismatch between satellite sensors and smallholder fields, and 2) a lack of high-quality labels needed to train and assess machine learning classifiers. We developed an approach designed to address these two problems, and used it to map Ghana’s croplands. To overcome the spatio-temporal mismatch, we converted daily, high resolution imagery into two cloud-free composites (the primary growing season and subsequent dry season) covering the 2018 agricultural year, providing a seasonal contrast that helps to improve classification accuracy. To address the problem of label availability, we created a platform that rigorously assesses and minimizes label error, and used it to iteratively train a Random Forests classifier with active learning, which identifies the most informative training sample based on prediction uncertainty. Minimizing label errors improved model F1 scores by up to 25%. Active learning increased F1 scores by an average of 9.1% between first and last training iterations, and 2.3% more than models trained with randomly selected labels. We used the resulting 3.7 m map of cropland probabilities within a segmentation algorithm to delineate crop field boundaries. Using an independent map reference sample (n = 1,207), we found that the cropland probability and field boundary maps had respective overall accuracies of 88 and 86.7%, user’s accuracies for the cropland class of 61.2 and 78.9%, and producer’s accuracies of 67.3 and 58.2%. An unbiased area estimate calculated from the map reference sample indicates that cropland covers 17.1% (15.4–18.9%) of Ghana. Using the most accurate validation labels to correct for biases in the segmented field boundaries map, we estimated that the average size and total number of field in Ghana are 1.73 ha and 1,662,281, respectively. Our results demonstrate an adaptable and transferable approach for developing annual, country-scale maps of crop field boundaries, with several features that effectively mitigate the errors inherent in remote sensing of smallholder-dominated agriculture.

Crop Type Mapping from Optical and Radar Time Series Using Attention-Based Deep Learning

Crop maps are key inputs for crop inventory production and yield estimation and can inform the implementation of effective farm management practices. Producing these maps at detailed scales requires exhaustive field surveys that can be laborious, time-consuming, and expensive to replicate. With a growing archive of remote sensing data, there are enormous opportunities to exploit dense satellite image time series (SITS), temporal sequences of images over the same area. Generally, crop type mapping relies on single-sensor inputs and is solved with the help of traditional learning algorithms such as random forests or support vector machines. Nowadays, deep learning techniques have brought significant improvements by leveraging information in both spatial and temporal dimensions, which are relevant in crop studies. The concurrent availability of Sentinel-1 (synthetic aperture radar) and Sentinel-2 (optical) data offers a great opportunity to utilize them jointly; however, optimizing their synergy has been understudied with deep learning techniques. In this work, we analyze and compare three fusion strategies (input, layer, and decision levels) to identify the best strategy that optimizes optical-radar classification performance. They are applied to a recent architecture, notably, the pixel-set encoder–temporal attention encoder (PSE-TAE) developed specifically for object-based classification of SITS and based on self-attention mechanisms. Experiments are carried out in Brittany, in the northwest of France, with Sentinel-1 and Sentinel-2 time series. Input and layer-level fusion competitively achieved the best overall F-score surpassing decision-level fusion by 2%. On a per-class basis, decision-level fusion increased the accuracy of dominant classes, whereas layer-level fusion improves up to 13% for minority classes. Against single-sensor baseline, multi-sensor fusion strategies identified crop types more accurately: for example, input-level outperformed Sentinel-2 and Sentinel-1 by 3% and 9% in F-score, respectively. We have also conducted experiments that showed the importance of fusion for early time series classification and under high cloud cover condition.

Delineating Smallholder Maize Farms from Sentinel-1 Coupled with Sentinel-2 Data Using Machine Learning

Rural communities rely on smallholder maize farms for subsistence agriculture, the main driver of local economic activity and food security. However, their planted area estimates are unknown in most developing countries. This study explores the use of Sentinel-1 and Sentinel-2 data to map smallholder maize farms. The random forest (RF), support vector (SVM) machine learning algorithms and model stacking (ST) were applied. Results show that the classification of combined Sentinel-1 and Sentinel-2 data improved the RF, SVM and ST algorithms by 24.2%, 8.7%, and 9.1%, respectively, compared to the classification of Sentinel-1 data individually. Similarities in the estimated areas (7001.35 ± 1.2 ha for RF, 7926.03 ± 0.7 ha for SVM and 7099.59 ± 0.8 ha for ST) show that machine learning can estimate smallholder maize areas with high accuracies. The study concludes that the single-date Sentinel-1 data were insufficient to map smallholder maize farms. However, single-date Sentinel-1 combined with Sentinel-2 data were sufficient in mapping smallholder farms. These results can be used to support the generation and validation of national crop statistics, thus contributing to food security.

Evaluation of Crop Type Classification with Different High Resolution Satellite Data Sources

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.

Comparative Analysis of Edge Information and Polarization on SAR-to-Optical Translation Based on Conditional Generative Adversarial Networks

To accurately describe dynamic vegetation changes, high temporal and spectral resolution data are urgently required. Optical images contain rich spectral information but are limited by poor weather conditions and cloud contamination. Conversely, synthetic-aperture radar (SAR) is effective under all weather conditions but contains insufficient spectral information to recognize certain vegetation changes. Conditional adversarial networks (cGANs) can be adopted to transform SAR images (Sentinel-1) into optical images (Landsat8), which exploits the advantages of both optical and SAR images. As the features of SAR and optical remote sensing data play a decisive role in the translation process, this study explores the quantitative impact of edge information and polarization (VV, VH, VV&VH) on the peak signal-to-noise ratio, structural similarity index measure, correlation coefficient (r), and root mean squared error. The addition of edge information improves the structural similarity between generated and real images. Moreover, using the VH and VV&VH polarization modes as the input provides the cGANs with more effective information and results in better image quality. The optimal polarization mode with the addition of edge information is VV&VH, whereas that without edge information is VV. Near-infrared and short-wave infrared bands in the generated image exhibit higher accuracy (r > 0.8) than visible light bands. The conclusions of this study could serve as an important reference for selecting cGANs input features, and as a potential reference for the applications of cGANs to the SAR-to-optical translation of other multi-source remote sensing data.

Kc and LAI Estimations Using Optical and SAR Remote Sensing Imagery for Vineyards Plots

Daily or weekly irrigation monitoring conducted per sub-field or management zone is an important factor in vine irrigation decision-making. The objective is to determine the crop coefficient (Kc) and the leaf area index (LAI). Since the 1990s, optic satellite imagery has been utilized for this purpose, yet cloud-cover, as well as the desire to increase the temporal resolution, raise the need to integrate more imagery sources. The Sentinel-1 (a C-band synthetic aperture radar—SAR) can solve both issues, but its accuracy for LAI and Kc mapping needs to be determined. The goals of this study were as follows: (1) to test different methods for integrating SAR and optic sensors for increasing temporal resolution and creating seamless time-series of LAI and Kc estimations; and (2) to evaluate the ability of Sentinel-1 to estimate LAI and Kc in comparison to Sentinel-2 and Landsat-8. LAI values were collected at two vineyards, over three (north plot) and four (south plot) growing seasons. These values were converted to Kc, and both parameters were tested against optic and SAR indices. The results present the two Sentinel-1 indices that achieved the best accuracy in estimating the crop parameters and the best method for fusing the optic and the SAR data. Utilizing these achievements, the accuracy of the Kc and LAI estimations from Sentinel-1 were slightly better than the Sentinel-2′s and the Landsat-8′s accuracy. The integration of all three sensors into one seamless time-series not only increases the temporal resolution but also improves the overall accuracy.

Unsupervised Parameterization for Optimal Segmentation of Agricultural Parcels from Satellite Images in Different Agricultural Landscapes

Image segmentation is a cost-effective way to obtain information about the sizes and structural composition of agricultural parcels in an area. To accurately obtain such information, the parameters of the segmentation algorithm ought to be optimized using supervised or unsupervised methods. The difficulty in obtaining reference data makes unsupervised methods indispensable. In this study, we evaluated an existing unsupervised evaluation metric that minimizes a global score (GS), which is computed by summing up the intra-segment uniformity and inter-segment dissimilarity within a segmentation output. We modified this metric and proposed a new metric that uses absolute difference to compute the GS. We compared this proposed metric with the existing metric in two optimization approaches based on the Multiresolution Segmentation (MRS) algorithm to optimally delineate agricultural parcels from Sentinel-2 images in Lower Saxony, Germany. The first approach searches for optimal scale while keeping shape and compactness constant, while the second approach uses Bayesian optimization to optimize the three main parameters of the MRS algorithm. Based on a reference data of agricultural parcels, the optimal segmentation result of each optimization approach was evaluated by calculating the quality rate, over-segmentation, and under-segmentation. For both approaches, our proposed metric outperformed the existing metric in different agricultural landscapes. The proposed metric identified optimal segmentations that were less under-segmented compared to the existing metric. A comparison of the optimal segmentation results obtained in this study to existing benchmark results generated via supervised optimization showed that the unsupervised Bayesian optimization approach based on our proposed metric can potentially be used as an alternative to supervised optimization, particularly in geographic regions where reference data is unavailable or an automated evaluation system is sought.

Crop Type Classification Using Fusion of Sentinel-1 and Sentinel-2 Data: Assessing the Impact of Feature Selection, Optical Data Availability, and Parcel Sizes on the Accuracies

Crop type classification using Earth Observation (EO) data is challenging, particularly for crop types with similar phenological growth stages. In this regard, the synergy of optical and Synthetic-Aperture Radar (SAR) data enables a broad representation of biophysical and structural information on target objects, enhancing crop type mapping. However, the fusion of multi-sensor dense time-series data often comes with the challenge of high dimensional feature space. In this study, we (1) evaluate how the usage of only optical, only SAR, and their fusion affect the classification accuracy; (2) identify the combination of which time-steps and feature-sets lead to peak accuracy; (3) analyze misclassifications based on the parcel size, optical data availability, and crops’ temporal profiles. Two fusion approaches were considered and compared in this study: feature stacking and decision fusion. To distinguish the most relevant feature subsets time- and variable-wise, grouped forward feature selection (gFFS) was used. gFFS allows focusing analysis and interpretation on feature sets of interest like spectral bands, vegetation indices (VIs), or data sensing time rather than on single features. This feature selection strategy leads to better interpretability of results while substantially reducing computational expenses. The results showed that, in contrast to most other studies, SAR datasets outperform optical datasets. Similar to most other studies, the optical-SAR combination outperformed single sensor predictions. No significant difference was recorded between feature stacking and decision fusion. Random Forest (RF) appears to be robust to high feature space dimensionality. The feature selection did not improve the accuracies even for the optical-SAR feature stack with 320 features. Nevertheless, the combination of RF feature importance and time- and variable-wise gFFS rankings in one visualization enhances interpretability and understanding of the features’ relevance for specific classification tasks. For example, by enabling the identification of features that have high RF feature importance values but are, in their information content, correlated with other features. This study contributes to the growing domain of interpretable machine learning.

Mapping Maize Fields by Using Multi-Temporal Sentinel-1A and Sentinel-2A Images in Makarfi, Northern Nigeria, Africa

A timely and accurate crop type mapping is very significant, and a prerequisite for agricultural regions and ensuring global food security. The combination of remotely sensed optical and radar datasets presents an opportunity for acquiring crop information at relative spatial resolution and temporal resolution adequately to capture the growth profiles of various crop species. In this paper, we employed Sentinel-1A (S-1) and Sentinel-2A (S-2) data acquired between the end of June and early September 2016, on a semi-arid area in northern Nigeria. A different set of (VV and VH) SAR and optical (SI and SB) images, illustrating crop phenological development stage, were employed as inputs to the two machines learning Random Forest (RF) and Support Vector Machine (SVM) algorithms to automatically map maize fields. Significant increases in overall classification were shown when the multi-temporal spectral indices (SI) and spectral band (SB) datasets were added with the different integration of SAR datasets (i.e., VV and VH). The best overall accuracy (OA) for maize (96.93%) was derived by using RF classification algorithms with SI-SB-SAR datasets, although the SI datasets for RF and SB datasets for SVM also produced high overall maize classification accuracies, of 97.04% and 97.44%. The outcomes indicate the robustness of the RF or SVM methods to produce high-resolution maps of maize for subsequent application from agronomists, policy planners, and the government, because such information is lacking in our study area.

Synergistic Use of Multi-Temporal RADARSAT-2 and VENµS Data for Crop Classification Based on 1D Convolutional Neural Network

Annual crop inventory information is important for many agriculture applications and government statistics. The synergistic use of multi-temporal polarimetric synthetic aperture radar (SAR) and available multispectral remote sensing data can reduce the temporal gaps and provide the spectral and polarimetric information of the crops, which is effective for crop classification in areas with frequent cloud interference. The main objectives of this study are to develop a deep learning model to map agricultural areas using multi-temporal full polarimetric SAR and multi-spectral remote sensing data, and to evaluate the influence of different input features on the performance of deep learning methods in crop classification. In this study, a one-dimensional convolutional neural network (Conv1D) was proposed and tested on multi-temporal RADARSAT-2 and VENµS data for crop classification. Compared with the Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN) and non-deep learning methods including XGBoost, Random Forest (RF), and Support Vector Machina (SVM), the Conv1D performed the best when the multi-temporal RADARSAT-2 data (Pauli decomposition or coherency matrix) and VENµS multispectral data were fused by the Minimum Noise Fraction (MNF) transformation. The Pauli decomposition and coherency matrix gave similar overall accuracy (OA) for Conv1D when fused with the VENµS data by the MNF transformation (OA = 96.65 ± 1.03% and 96.72 ± 0.77%). The MNF transformation improved the OA and F-score for most classes when Conv1D was used. The results reveal that the coherency matrix has a great potential in crop classification and the MNF transformation of multi-temporal RADARSAT-2 and VENµS data can enhance the performance of Conv1D.

Combining Deep Learning and Prior Knowledge for Crop Mapping in Tropical Regions from Multitemporal SAR Image Sequences

Accurate crop type identification and crop area estimation from remote sensing data in tropical regions are still considered challenging tasks. The more favorable weather conditions, in comparison to the characteristic conditions of temperate regions, permit higher flexibility in land use, planning, and management, which implies complex crop dynamics. Moreover, the frequent cloud cover prevents the use of optical data during large periods of the year, making SAR data an attractive alternative for crop mapping in tropical regions. This paper evaluates the effectiveness of Deep Learning (DL) techniques for crop recognition from multi-date SAR images from tropical regions. Three DL strategies are investigated: autoencoders, convolutional neural networks, and fully-convolutional networks. The paper further proposes a post-classification technique to enforce prior knowledge about crop dynamics in the target area. Experiments conducted on a Sentinel-1 multitemporal sequence of a tropical region in Brazil reveal the pros and cons of the tested methods. In our experiments, the proposed crop dynamics model was able to correct up to 16.5% of classification errors and managed to improve the performance up to 3.2% and 8.7% in terms of overall accuracy and average F1-score, respectively.

Crop Classification Based on Temporal Information Using Sentinel-1 SAR Time-Series Data

With the increasing temporal resolution of space-borne SAR, large amounts of intensity data are now available for continues land observations. Previous researches proved the effectiveness of multitemporal SAR in land classification, but the characterizations of temporal information were still inadequate. In this paper, we proposed a crop classification scheme, which made full use of multitemporal SAR backscattering responses. In this method, the temporal intensity models were established by the K-means clustering method. The intensity vectors were treated as input features, and the mean intensity vectors of cluster centers were regarded as the temporal models. The temporal models summarized the backscatter evolutions of crops and were utilized as the criterion for crop discrimination. The spectral similarity value (SSV) measure was introduced from hyperspectral image processing for temporal model matching. The unlabeled pixel was assigned to the class to which the temporal model with the highest similarity belonged. Two sets of Sentinel-1 SAR time-series data were used to illustrate the effectiveness of the proposed method. The comparison between SSV and other measures demonstrated the superiority of SSV in temporal model matching. Compared with the decision tree (DT) and naive Bayes (NB) classifiers, the proposed method achieved the best overall accuracies in both VH and VV bands. For most crops, it either obtained the best accuracies or achieved comparable accuracies to the best ones, which illustrated the effectiveness of the proposed method.

Mapping Mangrove Extent and Change: A Globally Applicable Approach

This study demonstrates a globally applicable method for monitoring mangrove forest extent at high spatial resolution. A 2010 mangrove baseline was classified for 16 study areas using a combination of ALOS PALSAR and Landsat composite imagery within a random forests classifier. A novel map-to-image change method was used to detect annual and decadal changes in extent using ALOS PALSAR/JERS-1 imagery. The map-to-image method presented makes fewer assumptions of the data than existing methods, is less sensitive to variation between scenes due to environmental factors (e.g., tide or soil moisture) and is able to automatically identify a change threshold. Change maps were derived from the 2010 baseline to 1996 using JERS-1 SAR and to 2007, 2008 and 2009 using ALOS PALSAR. This study demonstrated results for 16 known hotspots of mangrove change distributed globally, with a total mangrove area of 2,529,760 ha. The method was demonstrated to have accuracies consistently in excess of 90% (overall accuracy: 92.2–93.3%, kappa: 0.86) for mapping baseline extent. The accuracies of the change maps were more variable and were dependent upon the time period between images and number of change features. Total change from 1996 to 2010 was 204,850 ha (127,990 ha gain, 76,860 ha loss), with the highest gains observed in French Guiana (15,570 ha) and the highest losses observed in East Kalimantan, Indonesia (23,003 ha). Changes in mangrove extent were the consequence of both natural and anthropogenic drivers, yielding net increases or decreases in extent dependent upon the study site. These updated maps are of importance to the mangrove research community, particularly as the continual updating of the baseline with currently available and anticipated spaceborne sensors. It is recommended that mangrove baselines are updated on at least a 5-year interval to suit the requirements of policy makers.

Soil and Water Conservation in Burkina Faso, West Africa

Inadequate land management and agricultural activities have largely resulted in land degradation in Burkina Faso. The nationwide governmental and institutional driven implementation and adoption of soil and water conservation measures (SWCM) since the early 1960s, however, is expected to successively slow down the degradation process and to increase the agricultural output. Even though relevant measures have been taken, only a few studies have been conducted to quantify their effect, for instance, on soil erosion and environmental restoration. In addition, a comprehensive summary of initiatives, implementation strategies, and eventually region-specific requirements for adopting different SWCM is missing. The present study therefore aims to review the different SWCM in Burkina Faso and implementation programs, as well as to provide information on their effects on environmental restoration and agricultural productivity. This was achieved by considering over 143 studies focusing on Burkina Faso’s experience and research progress in areas of SWCM and soil erosion. SWCM in Burkina Faso have largely resulted in an increase in agricultural productivity and improvement in food security. Finally, this study aims at supporting the country’s informed decision-making for extending already existing SWCM and for deriving further implementation strategies.

A framework to assess landscape structural capacity to provide regulating ecosystem services in West Africa

The Sudanian savanna landscapes of West Africa are amongst the world's most vulnerable areas to climate change impacts. Inappropriate land use and agriculture management practices continuously impede the capacity of agricultural landscapes to provide ecosystem services (ES). Given the absence of practical assessment techniques to evaluate the landscape's capacity to provide regulating ES in this region, the goal of this paper is to propose an integrative assessment framework which combines remote sensing, geographic information systems, expert weighting and landscape metrics-based assessment. We utilized Analytical Hierarchical Process and Likert scale for the expert weighting of landscape capacity. In total, 56 experts from several land use and landscape management related departments participated in the assessment. Further, we adapted the hemeroby concept to define areas of naturalness while landscape metrics including Patch Density, Shannon's Diversity, and Shape Index were utilized for structural assessment. Lastly, we tested the reliability of expert weighting using certainty measurement rated by experts themselves. Our study focused on four regulating ES including flood control, pest and disease control, climate control, and wind erosion control. Our assessment framework was tested on four selected sites in the Vea catchment area of Ghana. The outcome of our study revealed that highly heterogeneous landscapes have a higher capacity to provide pest and disease control, while less heterogeneous landscapes have a higher potential to provide climate control. Further, we could show that the potential capacities to provide ecosystem services are underestimated by 15% if landscape structural aspects assessed through landscape metrics are not considered. We conclude that the combination of adapted land use and an optimized land use pattern could contribute considerably to lower climate change impacts in West African agricultural landscapes.

Maize Cropping Systems Mapping Using RapidEye Observations in Agro-Ecological Landscapes in Kenya

Cropping systems information on explicit scales is an important but rarely available variable in many crops modeling routines and of utmost importance for understanding pests and disease propagation mechanisms in agro-ecological landscapes. In this study, high spatial and temporal resolution RapidEye bio-temporal data were utilized within a novel 2-step hierarchical random forest (RF) classification approach to map areas of mono- and mixed maize cropping systems. A small-scale maize farming site in Machakos County, Kenya was used as a study site. Within the study site, field data was collected during the satellite acquisition period on general land use/land cover (LULC) and the two cropping systems. Firstly, non-cropland areas were masked out from other land use/land cover using the LULC mapping result. Subsequently an optimized RF model was applied to the cropland layer to map the two cropping systems (2nd classification step). An overall accuracy of 93% was attained for the LULC classification, while the class accuracies (PA: producer’s accuracy and UA: user’s accuracy) for the two cropping systems were consistently above 85%. We concluded that explicit mapping of different cropping systems is feasible in complex and highly fragmented agro-ecological landscapes if high resolution and multi-temporal satellite data such as 5 m RapidEye data is employed. Further research is needed on the feasibility of using freely available 10–20 m Sentinel-2 data for wide-area assessment of cropping systems as an important variable in numerous crop productivity models.

Mapping Winter Wheat with Multi-Temporal SAR and Optical Images in an Urban Agricultural Region

Winter wheat is the second largest food crop in China. It is important to obtain reliable winter wheat acreage to guarantee the food security for the most populous country in the world. This paper focuses on assessing the feasibility of in-season winter wheat mapping and investigating potential classification improvement by using SAR (Synthetic Aperture Radar) images, optical images, and the integration of both types of data in urban agricultural regions with complex planting structures in Southern China. Both SAR (Sentinel-1A) and optical (Landsat-8) data were acquired, and classification using different combinations of Sentinel-1A-derived information and optical images was performed using a support vector machine (SVM) and a random forest (RF) method. The interference coherence and texture images were obtained and used to assess the effect of adding them to the backscatter intensity images on the classification accuracy. The results showed that the use of four Sentinel-1A images acquired before the jointing period of winter wheat can provide satisfactory winter wheat classification accuracy, with an F1 measure of 87.89%. The combination of SAR and optical images for winter wheat mapping achieved the best F1 measure-up to 98.06%. The SVM was superior to RF in terms of the overall accuracy and the kappa coefficient, and was faster than RF, while the RF classifier was slightly better than SVM in terms of the F1 measure. In addition, the classification accuracy can be effectively improved by adding the texture and coherence images to the backscatter intensity data.