Enhanced mapping of a smallholder crop farming landscape through image fusion and model stacking

Abstract

Globally, Smallholder farming systems (SFS) are recognized as one of the most important pillars of rural economic development and poverty alleviation because of their contribution to food security. However, support for this agricultural sector is hampered by lack of reliable information on the distributions and acreage of smallholder fields. This information is essential in not only monitoring food security and informing markets but also in guiding the determination of levels of support required from government by individual farmers. There is urgent need for robust techniques that can be used to cost-effectively and time-efficiently map smallholder crop fields especially in Sub-Saharan Africa and Asia. This study attempts to do this by using an approach in which optical and Synthetic Aperture Radar (SAR) data are systematically combined and classified using Extreme Gradient Boosting (Xgboost). We also investigated model stacking as another technique to improve classification accuracy. We combined Xgboost with Random Forest (RF), Support Vector Machine (SVM), Artificial Neural Networks (ANN), and Naïve Bayes (NB). The combined use of multi-temporal Sentinel-2 bands, spectral indices, and Sentinel-1 produced better results than exclusive use of optical data (α = 0.95, p = 0.0005). Furthermore, stacking of classification algorithms based on model comparisons achieved higher accuracy than stacking the algorithms indiscriminately (α = 0.95, p = 0.0100). Through systematic fusion of SAR and optical data and hyper-parameter tuning of Xgboost, we achieved a maximum classification accuracy of 97.71%, while achieving a maximum accuracy of 96.06% through model stacking. This highlights the importance of multi-sensor data fusion and multi-classifier systems when mapping fragmented agricultural landscapes.

Improved Accuracy of Phenological Detection in Rice Breeding by Using Ensemble Models of Machine Learning Based on UAV-RGB Imagery

“…Our results emphasized that the strategies to combine individual classifiers had the potential to improve phenology classification. This is consistent with literature that finds that ensemble models outperformed individual machine learning algorithms in many applications, such as mapping smallholder fields [37], predicting invasive plants [62] and forecasting corn yield [36].…”

“…Shahhosseini et al [36] combined linear, least absolute shrinkage and selection operator (LASSO), eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM) and random forests (RF) to forecast corn yield. Masiza et al [37] combined XGBoost with support vector machine (SVM), artificial neural network (ANN), naïve Bayes (NB) and RF to map landscape in a smallholder farming system. Although some ensemble methods have been applied in agriculture domain, to the best of our knowledge, the performance and potential of different ensemble models are rarely compared and tested for detecting phenology.…”

Crop Area Mapping in Southern and Central Malawi With Google Earth Engine

“…They are also quite coarse, being reported at the administrative unit level for ground-based statistics, and generally, 300-1,000 m pixels for satellite-based maps (Carletto et al, 2015;Samasse et al, 2018). The recent availability of 10 m Sentinel-2 data in Google Earth Engine (GEE) allows for efficient processing of high spatial resolution data, making high spatial resolution crop area maps over large areas feasible (Chivasa et al, 2017;Samasse et al, 2018;Jin et al, 2019;Amani et al, 2020;Karlson et al, 2020;Kerner et al, 2020;Masiza et al, 2020;Tseng et al, 2020;Verde et al, 2020).…”

“…Most of the studies using crop phenology to map crop area use either raw bands, vegetation indices (VIs) such as the Normalized Difference Vegetation Index (NDVI, Rouse et al, 1973), or a combination of the two (Samasse et al, 2018;Jin et al, 2019;Amani et al, 2020;Karlson et al, 2020;Kerner et al, 2020;Masiza et al, 2020;Tseng et al, 2020;Verde et al, 2020). In this study we took a different approach.…”

Feature Extraction and Image Retrieval of Landscape Images Based on Image Processing

“…Landscape images provide the most intuitive and accurate expression of landscape, by feat of the various carriers of characteristic information, such as hierarchy, layout, color system, and color matching [1][2][3]. Facing the existing digital image libraries with the theme of landscape design, researchers need to urgently realize the management and retrieval of landscape images, based on their understanding of image attributes (texture and color) and image contents (hierarchy) [4][5][6][7].…”