Multi-Year Cereal Crop Classification Model in a Semi-Arid Region Using Sentinel-2 and Landsat 7–8 Data

Abstract

This study developed a multi-year classification model for winter cereal in a semi-arid region, the Kairouan area (Tunisia). A random forest classification model was constructed using Sentinel 2 (S2) vegetation indices for a reference agricultural season, 2020/2021. This model was then applied using S2 and Landsat (7 and 8) data for previous seasons from 2011 to 2022 and validated using field observation data. The reference classification model achieved an overall accuracy (OA) of 89.3%. Using S2 data resulted in higher overall classification accuracy. Cereal classification exhibited excellent precision ranging from 85.8% to 95.1% when utilizing S2 data, while lower accuracy (41% to 91.8%) was obtained when using only Landsat data. A slight confusion between cereals and cereals growing with olive trees was observed. A second objective was to map cereals as early as possible in the agricultural season. An early cereal classification model demonstrated accurate results in February (four months before harvest), with a precision of 95.2% and an OA of 87.7%. When applied to the entire period, February cereal classification exhibited a precision ranging from 85.1% to 94.2% when utilizing S2 data, while lower accuracy (42.6% to 95.4%) was observed in general with Landsat data. This methodology could be adopted in other cereal regions with similar climates to produce very useful information for the planner, leading to a reduction in fieldwork.

Water Footprint of Cereals by Remote Sensing in Kairouan Plain (Tunisia)

“…For instance, in the 2013 scatterplot, an abundance of pixels with low yield but varying WF from 1 to 6 can be observed, indicating the influence of diverse soils and cultural practices. These specific areas identified through this spatial study should undergo closer examination to validate this hypothesis [26,59].…”

“…The regression model spatialized the grain cereal yield across the entire Kairouan plain using NDVI images for the three agricultural years 2010-2011, 2011-2012, and 2012-2013. The agricultural year 2011/2012, characterized by heavy rains during the cereal vegetative cycle, witnessed a larger number of fields cultivated with cereals [59,60]. A comparison between the 2010-2011 and 2011-2012 seasons reveals that plots abandoned in the first year became productive in the subsequent year due to the abundant rainfall, even though their yields were relatively low.…”