Land use mapping using Sentinel-1 and Sentinel-2 time series in a heterogeneous landscape in Niger, Sahel

Schulz, Dario; Yin, He; Tischbein, Bernhard; Verleysdonk, Sarah; Adamou, Rabani; Kumar, Navneet

doi:10.1016/j.isprsjprs.2021.06.005

Cited by 75 publications

(55 citation statements)

References 83 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We calculated a total of 11 pixel-based statistics: Minimum (Min), 25% Quantile (Q25), 50% Quantile (Q50), 75% Quantile The 770-dimensional feature space is large, consisting of redundant and correlated features, which do not add important information to the RF classifier but increase computational complexity, storage space, and classification run time [54][55][56]. Therefore, we applied recursive feature elimination within a cross-validated setup using the scikit-learn RFECVclass in Python.…”

Section: Phenology and Spectral-temporal Metricsmentioning

confidence: 99%

Mapping Crop Types and Cropping Systems in Nigeria with Sentinel-2 Imagery

et al. 2021

View full text Add to dashboard Cite

Reliable crop type maps from satellite data are an essential prerequisite for quantifying crop growth, health, and yields. However, such maps do not exist for most parts of Africa, where smallholder farming is the dominant system. Prevalent cloud cover, small farm sizes, and mixed cropping systems pose substantial challenges when creating crop type maps for sub-Saharan Africa. In this study, we provide a mapping scheme based on freely available Sentinel-2A/B (S2) time series and very high-resolution SkySat data to map the main crops—maize and potato—and intercropping systems including these two crops on the Jos Plateau, Nigeria. We analyzed the spectral-temporal behavior of mixed crop classes to improve our understanding of inter-class spectral mixing. Building on the Framework for Operational Radiometric Correction for Environmental monitoring (FORCE), we preprocessed S2 time series and derived spectral-temporal metrics from S2 spectral bands for the main temporal cropping windows. These STMs were used as input features in a hierarchical random forest classification. Our results provide the first wall-to-wall crop type map for this key agricultural region of Nigeria. Our cropland identification had an overall accuracy of 84%, while the crop type map achieved an average accuracy of 72% for the five relevant crop classes. Our crop type map shows distinctive regional variations in the distribution of crop types. Maize is the dominant crop, followed by mixed cropping systems, including maize–cereals and potato–maize cropping; potato was found to be the least prevalent class. Plot analyses based on a sample of 1166 fields revealed largely homogeneous mapping patterns, demonstrating the effectiveness of our classification system also for intercropped classes, which are temporally and spatially highly heterogeneous. Moreover, we found that small field sizes were dominant in all crop types, regardless of whether or not intercropping was used. Maize–legume and maize exhibited the largest plots, with an area of up to 3 ha and slightly more than 10 ha, respectively; potato was mainly cultivated on fields smaller than 0.5 ha and only a few plots were larger than 1 ha. Besides providing the first spatially explicit map of cropping practices in the core production area of the Jos Plateau, Nigeria, the study also offers guidance for the creation of crop type maps for smallholder-dominated systems with intercropping. Critical temporal windows for crop type differentiation will enable the creation of mapping approaches in support of future smart agricultural practices for aspects such as food security, early warning systems, policies, and extension services.

show abstract

Section: Phenology and Spectral-temporal Metricsmentioning

confidence: 99%

Mapping Crop Types and Cropping Systems in Nigeria with Sentinel-2 Imagery

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Scenes taken in descending orbit were chosen to be processed for LU/LC classification. And speckle effects were filtered using the median filter, according to (Schulz et al 2021).…”

Section: Data Used and Processingmentioning

confidence: 99%

“…According to the proposed GEE script, the ROIs were divided as 75% for training and 25% for validation process. The pixel-based image classification was applied using the random forest classifier (Schulz et al 2021;Vogels et al 2019) within GEE. In addition, the validation overall accuracy was calculated, and confusion matrix was obtained within GEE.…”

Section: Land Use/cover Classificationmentioning

confidence: 99%

Land Use/Cover Changes in Al-Jouf, KSA in Response to Water Management Strategies Using Multi-Sensor/-Temporal Data in Google Earth Engine

Mahmoud

2022

Scientific Journal of Agricultural Sciences

View full text Add to dashboard Cite

The water resources are limited and need to be managed in different demand areas. As agriculture consumes the major quantity of water, thus water management is an essential process. In KSA, new regulations have been issued to manage the water consumption in agriculture. This led to a shift within agriculture use from the more consumption crops to the lower ones in some areas, apart from the areas that stopped cultivation activity. This study aims at evaluating the land use/cover changes within an agricultural area in Al-Jouf region, KSA. Therefore, multi-temporal Sentinel-1 (S-1) and Sentinel-2 (S-2) data were analyzed with the aid of the valuable capabilities of the cloud-based platform Google Earth Engine (GEE). The cultivated areas during the period 2017 to 2021 were calculated based on monthly normalized difference vegetation index (NDVI). The results revealed a significant decrease in the annual average of cultivated area from 121,161 to 74,468 ha in 2021, with a high variation between winter and summer cultivated area. On the other hand, the multi-sensor/-temporal classification of S-1 and S-2 data showed a decrease in the agriculture area, and the shift to orchards. The orchards area increased by 84.0% (from 9,202 to 16,929 ha), the crops area decreased by 24.3% (from 125,512 to 95,016 ha), while the bare land increased by 9.7% (from 235,009 to 257,779 ha) as comparing areas in 2017 and 2021, respectively. The proposed approach provides near-real-time tracking of the changes in land use/cover for updating the water management strategies.

show abstract

“…Moreover, for high and very high spatial resolution (VHSR), remote sensing imagers are increasingly being used in LULC mapping analyses based on classification concepts using machine learning methods [3]. In recent decades, machine learning methods have been applied to remote sensing LULC classification tasks [4], [5], in particular, pixel-and objectbased image analysis (OBIA) methods [6], [7], particularly random forest (RF) [8]- [10], support vector machine (SVM) [11], [12], and artificial neural networks (ANNs) [13], [14]. As the most critical elements of image classification, the OBIA method is capable of identifying interspersed geographic features and objects [15].…”

Section: Introductionmentioning

confidence: 99%

Application of Convolutional Neural Networks With Object-Based Image Analysis for Land Cover and Land Use Mapping in Coastal Areas: A Case Study in Ain Témouchent, Algeria

Narimane

Niculescu

Mihoubi

2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Land use and land cover (LULC) information is a fundamental component of environmental research relating to urban planning, agricultural sustainability, and natural hazards assessment. In particular, remote sensing technology has demonstrated a powerful capacity for LULC modeling with a corresponding increase in sensor number and type. Here, an advanced convolutional neural network (CNN) deep learning model was developed in combination with object-based image analysis (OBIA) to map LULC in Ain Témouchent coastal area, western Algeria, using Sentinel-2 and Pléiades imagery data. First, the CNN model was constructed based on convolution, hidden, and max pooling layers. The parameters of CNN architecture were optimized to improve the model for further processing. Then, based on high levels of CNN feature extraction, the OBIA was applied to classify the segmented objects, and detect the LULC features.Furthermore, machine learning methods, including random forest (RF) and support vector machines (SVM) were tested for comparison. The proposed method achieved a high overall accuracy (93.5%) using Pléiades imagery, revealing significant improvements compared to other machine learning techniques. Accordingly, it was concluded that the method proposed here is useful for LULC detection, and can be applied at larger scales in coastal areas. The derived maps can also inform regional and national-level decision making.

show abstract

Land use mapping using Sentinel-1 and Sentinel-2 time series in a heterogeneous landscape in Niger, Sahel

Cited by 75 publications

References 83 publications

Mapping Crop Types and Cropping Systems in Nigeria with Sentinel-2 Imagery

Mapping Crop Types and Cropping Systems in Nigeria with Sentinel-2 Imagery

Land Use/Cover Changes in Al-Jouf, KSA in Response to Water Management Strategies Using Multi-Sensor/-Temporal Data in Google Earth Engine

Application of Convolutional Neural Networks With Object-Based Image Analysis for Land Cover and Land Use Mapping in Coastal Areas: A Case Study in Ain Témouchent, Algeria

Contact Info

Product

Resources

About