Crop NDVI Monitoring Based on Sentinel 1

Abstract

Monitoring agricultural crops is necessary for decision-making in the field. However, it is known that in some regions and periods, cloud cover makes this activity difficult to carry out in a systematic way throughout the phenological cycle of crops. This circumstance opens up opportunities for techniques involving radar sensors, resulting in images that are free of cloud effects. In this context, the objective of this work was to obtain a normalized different vegetation index (NDVI) cloudless product (NDVInc) by modeling Sentinel 2 NDVI using different regression techniques and the Sentinel 1 radar backscatter as input. To do this, we used four pairs of Sentinel 2 and Sentinel 1 images on coincident days, aiming to achieve the greatest range of NDVI values for agricultural crops (soybean and maize). These coincident pairs were the only ones in which the percentage of clouds was not equal to 100% for 33 central pivot areas in western Bahia, Brazil. The dataset used for NDVInc modeling was divided into two subsets: training and validation. The training and validation datasets were from the period from 24 June 2017 to 19 July 2018 (four pairs of images). The best performing model was used in a temporal analysis from 02 October 2017 to 08 August 2018, totaling 55 Sentinel 2 images and 25 Sentinel 1 images. The selection of the best regression algorithm was based on two validation methodologies: K-fold cross-validation (k = 10) and holdout. We tested four modeling approaches with eight regression algorithms. The random forest was the algorithm that presented the best statistical metrics, regardless of the validation methodology and the approach used. Therefore, this model was applied to a time series of Sentinel 1 images in order to demonstrate the robustness and applicability of the model created. We observed that the data derived from Sentinel 1 allowed us to model, with great reliability, the NDVI of agricultural crops throughout the phenological cycle, making the methodology developed in this work a relevant solution for the monitoring of various regions, regardless of cloud cover.

Integration of Time Series Sentinel-1 and Sentinel-2 Imagery for Crop Type Mapping over Oasis Agricultural Areas

“…Another intensity-based ratio, the normalized ratio procedure between bands (NRPB) [31] is calculated as In summary, we derived 10 subcategories of features from Sentinel-1 data. Adding features of different acquisition dates together, 142 Sentinel-1 features were produced, geocoded, and resampled to 10 m resolution.…”

Untangling hybrid hydrological models with explainable artificial intelligence

“…Cubist regression is chosen in this study for two reasons. First, it allowed other authors to achieve state-of-art performance within a range of studies (Noi et al 2017;Worland et al 2018;Filgueiras et al 2019;Althoff et al 2020b), and second, it provided a good trade-off between performance and computational time (Althoff et al 2020b), which was an important aspect when considering the optimization task. For more information on cubist regressions, refer to Quinlan (1993).…”

Classification of Paddy Rice Using a Stacked Generalization Approach and the Spectral Mixture Method Based on MODIS Time Series

“…4). To avoid over-fitting and select the optimal hyper-parameters of different machine learning algorithms, the training samples were divided into k sets of the same size (D1, D2, …, Dk) by k-fold cross-validation and the stratified sampling method [61]. K-1 sets were selected as the training set, and the rest was the test set.…”