Mapping Center Pivot Irrigation Systems in the Southern Amazon from Sentinel-2 Images

Abstract

Irrigation systems play an important role in agriculture. Center pivot irrigation systems are popular in many countries as they are labor-saving and water consumption efficient. Monitoring the distribution of center pivot irrigation systems can provide important information for agricultural production, water consumption and land use. Deep learning has become an effective method for image classification and object detection. In this paper, a new method to detect the precise shape of center pivot irrigation systems is proposed. The proposed method combines a lightweight real-time object detection network (PVANET) based on deep learning, an image classification model (GoogLeNet) and accurate shape detection (Hough transform) to detect and accurately delineate center pivot irrigation systems and their associated circular shape. PVANET is lightweight and fast and GoogLeNet can reduce the false detections associated with PVANET, while Hough transform can accurately detect the shape of center pivot irrigation systems. Experiments with Sentinel-2 images in Mato Grosso achieved a precision of 95% and a recall of 95.5%, which demonstrated the effectiveness of the proposed method. Finally, with the accurate shape of center pivot irrigation systems detected, the area of irrigation in the region was estimated.

Dealing With Clouds and Seasonal Changes for Center Pivot Irrigation Systems Detection Using Instance Segmentation in Sentinel-2 Time Series

“…All DL models applied to optical imaging for center pivot detection reported training and applications for single-time imaging [47], [20], [57], [18], [58], [59], [17]. The main problems from only one date are clouds and visualizing the center pivot in particular planting stages.…”

“…1: Representation of the seasonal variations among center pivots in a Sentinel-2 image using the Red, Green, and Blue spectral bands. approaches: (a) detection of the core point of the center pivot [47]; (b) object detection with the establishment of bounding boxes around CPIS [20], [57]; (c) semantic segmentation that performs a pixel-wise classification where all CPIS pixels receive a label [18], [58], [59]; and (d) instance segmentation that produces bounding boxes and pixel-wise segmentation masks on CPIS [17].…”

Center Pivot Irrigation Systems as a Form of Drought Risk Mitigation in Humid Regions

“…While there has been a recent breakthrough in CPIS identification through deep learning methods in arid and semiarid regions where the distinctive crop circles left by CPIS are quite clear, humid regions like Illinois pose a greater difficulty due to the natural precipitation reducing the distinct boundary between the irrigated area and surrounding land cover most years (e.g. Zhang et al, 2018;Deines, et al, 2019;Saraiva et al, 2020;Valencia O. M., et al, 2020;Tang et al, 2021;Cooley, Maxwell, & Smith, 2021). However, we deployed a deep learning method that is able to predict the historical locations of CPIS in Illinois by using the pre-trained model described in Cooley et al (2021) based on the work of Saraiva et al (2020).…”

“…Athey, 2019;Storm, Baylis, & Heckelei, 2020), and to the growing literature regarding automated CPIS identification by examining a humid region rather than the more arid regions where similar models have been deployed (e.g. Zhang et al, 2018;Deines, et al, 2019;Saraiva et al, 2020;Valencia O. M., et al, 2020;Tang et al, 2021;Cooley, Maxwell, & Smith, 2021).…”

Physiology and Development of Soybean under Light Supplementation Treated with Herbicides in the Field

“…The irrigated area in Brazil is more than eight million hectares, and one of the irrigation methods is the central pivot sprinkler [4] (Tang et al, 2021). Light supplementation in soybeans with light-emitting diodes (LEDs) installed in the central irrigation pivot is under Agronomy 2024, 14, 824 2 of 15 study, with the purpose of improving environmental conditions to increase crop yield and quality.…”