Year-end Sale % OFF 
Abstract
Explicit spatial information about crop types on smallholder farms is important for the development of local precision agriculture. However, due to highly fragmented and heterogeneous cropland landscapes, fine-scale mapping of smallholder crops, based on low- and medium-resolution satellite images and relying on a single machine learning (ML) classifier, generally fails to achieve satisfactory performance. This paper develops an ensemble ML-based framework to improve the accuracy of parcel-level smallholder crop mapping from very high spatial resolution (VHSR) images. A typical smallholder agricultural area in central China covered by WorldView-2 images is selected to demonstrate our approach. This approach involves the task of distinguishing eight crop-level agricultural land use types. To this end, six widely used individual ML classifiers are evaluated. We further improved their performance by independently implementing bagging and stacking ensemble learning (EL) techniques. The results show that the bagging models improved the performance of unstable classifiers, but these improvements are limited. In contrast, the stacking models perform better, and the Stacking #2 model (overall accuracy = 83.91%, kappa = 0.812), which integrates the three best-performing individual classifiers, performs the best of all of the built models and improves the classwise accuracy of almost all of the land use types. Since classification performance can be significantly improved without adding costly data collection, stacking-ensemble mapping approaches are valuable for the spatial management of complex agricultural areas. We also demonstrate that using geometric and textural features extracted from VHSR images can improve the accuracy of parcel-level smallholder crop mapping. The proposed framework shows the great potential of combining EL technology with VHSR imagery for accurate mapping of smallholder crops, which could facilitate the development of parcel-level crop identification systems in countries dominated by smallholder agriculture.
Highlights
Smallholder farms with small plots and complex cropping practices are the most common and important forms of agriculture worldwide, accounting for approximately 87% of the world’s existing agricultural land and producing 70–80% of the world’s food [1,2]
The results show that the performance of all of the individual classifiers is generally good, with the overall accuracy (OA) ranging from 75.07% to 80.70%, kappa ranging from 0.707 to 0.775, and the weighted-F ranging from 0.752 to 0.808
Several ensemble models were built by applying bagging and stacking approaches separately on six widely used individual classifiers
Summary
Smallholder farms with small plots (typically ≤2 ha) and complex cropping practices are the most common and important forms of agriculture worldwide, accounting for approximately 87% of the world’s existing agricultural land and producing 70–80% of the world’s food [1,2]. Smallholder farming systems vary greatly in different countries and agricultural regions, they are generally characterized by limited farmland, decentralized management, and a low input-output ratio [3,4,5,6] The existence of these characteristics makes these systems vulnerable to global climate and environmental changes, explosive population growth, and market turmoil, posing serious threats to community food security and sustainable livelihoods [7,8,9]. In this context, timely and accurate mapping and monitoring of crop patterns on smallholder farms are critical for Remote Sens. Many studies have been conducted using RS technology to objectively identify and map crop types and planting intensity at national, regional, and other spatial scales [14,15,16,17,18]
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
