Comparing Sentinel-1, Sentinel-2, and Landsat-8 data in the early recognition of irrigated areas in central Italy

Abstract

This study evaluated the effectiveness of various remote sensing (RS) data (Sentinel-1, Sentinel-2, and Landsat 8) in the early recognition of irrigated areas in a densely cultivated area of central Italy. The study was based on crop data collected on more than 2000 plots in 2016 and 2017, characterized by quite different climatic conditions. The different RS data sources were used both alone and combined and with precipitation to define corresponding random forest (RF) classifiers whose overall accuracy (OA) was assessed by gradually increasing the number of available features from the beginning of the irrigation season. All tested RF classifiers reach stable OAs (OA 0.9) after 7-8 weeks from the start of the irrigation season. The performance of the radar indexes slightly improves when used in combination with precipitation data, but three weeks of features are required to obtain OA above 80%. The optical indices alone (Sentinel-2 and Landsat 8) reach OA ≈85% in the first week of observation. However, they are ineffective in cloudy conditions or when rainfed and irrigated fields have similar vigour. The most effective and robust indices are those based on combined sources (radar, optical, and meteorological), allowing OAs of about 92% and 96% at the beginning and in the middle of the irrigation season, respectively.