Mapping of cropland, cropping patterns and crop types by combining optical remote sensing images with decision tree classifier and random forest

ABSTRACT

Mapping and monitoring the distribution of croplands and crop types support policymakers and international organizations by reducing the risks to food security, notably from climate change and, for that purpose, remote sensing is routinely used. However, identifying specific crop types, cropland, and cropping patterns using space-based observations is challenging because different crop types and cropping patterns have similarity spectral signatures. This study applied a methodology to identify cropland and specific crop types, including tobacco, wheat, barley, and gram, as well as the following cropping patterns: wheat-tobacco, wheat-gram, wheat-barley, and wheat-maize, which are common in Gujranwala District, Pakistan, the study region. The methodology consists of combining optical remote sensing images from Sentinel-2 and Landsat-8 with Machine Learning (ML) methods, namely a Decision Tree Classifier (DTC) and a Random Forest (RF) algorithm. The best time-periods for differentiating cropland from other land cover types were identified, and then Sentinel-2 and Landsat 8 NDVI-based time-series were linked to phenological parameters to determine the different crop types and cropping patterns over the study region using their temporal indices and ML algorithms. The methodology was subsequently evaluated using Landsat images, crop statistical data for 2020 and 2021, and field data on cropping patterns. The results highlight the high level of accuracy of the methodological approach presented using Sentinel-2 and Landsat-8 images, together with ML techniques, for mapping not only the distribution of cropland, but also crop types and cropping patterns when validated at the county level. These results reveal that this methodology has benefits for monitoring and evaluating food security in Pakistan, adding to the evidence base of other studies on the use of remote sensing to identify crop types and cropping patterns in other countries.

KEYWORDS:

• Sentinel-2
• Random Forest
• cropland
• crop types
• cropping patterns
• Decision Tree Classifier

Acknowledgments

The authors wish to thank the editors and anonymous reviewers for their valuable comments and helpful suggestions. The authors would like to thank Stephen C. McClure for his enthusiastic support and valuable suggestions during the review of the manuscript.

Disclosure statement

The author declares that there is no conflict of interest in this manuscript’s publication. Moreover, the writers have thoroughly addressed ethical issues, including plagiarism, informed consent, fraud, data manufacturing and/or falsification, dual publication and/or submission and redundancy.

Data availability statement

We would like to thank to Sentinel Scientific Data Center of the European Space Agency (ESA) (https://doi.org/10.1080/10095020.2022.2100287) for the Sentinel-2 images and the United States Geological Survey (USGS) (https://doi.org/10.1080/10095020.2022.2100287) for the Landsat 8 images. We are also thankful to the Department of Agriculture & Farmer Welfare, Government of Punjab (https://doi.org/10.1080/10095020.2022.2100287), for providing us the crop statistical data for Gujranwala, Punjab, Pakistan.

Additional information

Notes on contributors

Aqil Tariq

Aqil Tariq received the MS degree in Remote Sensing and GIS from Pir-Mehr Ali Shah Arid Agriculture University, Rawalpindi, Pakistan, in 2016, and PhD degree in photogrammetry and remote sensing from the State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China. Now he is working in the LIESMARS, Wuhan University, China. His research interest areas are 3D Geoinformation, Urban analytics, spatial analysis to examine land use/land cover, Geospatial data science, Urban planning, Crop identification using SAR and Optical Satellite imagery, Agriculture monitoring, Forest Fire, Forest monitoring, forest cover dynamics, spatial statistics, multi-criteria algorithms, Ecosystem sustainability, Hazards risk reduction, Statistical analysis and modeling (Google Earth Engine, HEC-RAS, FlowR, RAMMS, GeoClaw, COSI-Corr, SfM) using Python, R and MATLAB.

Jianguo Yan

Jianguo Yan received his PhD degree from Wuhan University at 2007. He is working as full professor in the State Key Laboratory of Information Engineering in Surveying, Mapping, and Remote Sensing, Wuhan University, Wuhan, China. His current research interests include planetary spacecraft precise orbit determination, planetary gravity field recovery and its interior structure investigation. Recent work are precise orbit determination of MEX and Rosetta, and precise Mars lander positioning with various tracking techniques. The methods we employed are dynamic orbit determination theory, and inversion theory.

Alexandre S. Gagnon

Alexandre S. Gagnon received PhD degree and now he is working in the Biological and Environmental Sciences, James Parsons Building Byrom Street, Liverpool John Moores University. His research interest area are Hydrology, Geography, and Climatology.

Mobushir Riaz Khan

Mobushir Riaz Khan received PhD degree from ITC, University of Twente, Netherland. Now, he is working as professor in School of Agriculture Environment and Veterinary Sciences. His doctoral thesis focused on mapping and monitoring of crop production system using Remote Sensing and GIS along with crop production estimation using crop growth algorithms with remote sensing data. His research interest in geospatial analysis for agriculture, image processing, and environmental monitoring.

Faisal Mumtaz

Faisal Mumtaz received his master’s degree from Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China, in 2020. He is now pursuing his Doctoral degree from State key laboratory of remote sensing Science, (AIR-CAS). His main area of expertise is Urban and Infrared Remote Sensing, focusing mainly on Urban Heat Islands (UHI); Urban climate; Urban thermal environmental effects, human settlements; Spatio-temporal analysis, and climate system modeling.