Early Identification of Crop Type for Smallholder Farming Systems Using Deep Learning on Time-Series Sentinel-2 Imagery

Abstract

Climate change and the COVID-19 pandemic have disrupted the food supply chain across the globe and adversely affected food security. Early estimation of staple crops can assist relevant government agencies to take timely actions for ensuring food security. Reliable crop type maps can play an essential role in monitoring crops, estimating yields, and maintaining smooth food supplies. However, these maps are not available for developing countries until crops have matured and are about to be harvested. The use of remote sensing for accurate crop-type mapping in the first few weeks of sowing remains challenging. Smallholder farming systems and diverse crop types further complicate the challenge. For this study, a ground-based survey is carried out to map fields by recording the coordinates and planted crops in respective fields. The time-series images of the mapped fields are acquired from the Sentinel-2 satellite. A deep learning-based long short-term memory network is used for the accurate mapping of crops at an early growth stage. Results show that staple crops, including rice, wheat, and sugarcane, are classified with 93.77% accuracy as early as the first four weeks of sowing. The proposed method can be applied on a large scale to effectively map crop types for smallholder farms at an early stage, allowing the authorities to plan a seamless availability of food.

Fine-Scale (10 m) Dynamics of Smallholder Farming through COVID-19 in Eastern Thailand

“…Each sample point was located within at least a 10 m × 10 m area of a single crop type or a significantly dominant crop type, which was consistent with the spatial resolution of the satellite imagery used in this study (see Section 3.2). A total of 886 sample points were collected, predominantly consisting of major crop types, namely paddy rice (84), durian (57), eucalyptus (69), oil palm (85), pineapple (58), sugarcane (47), cassava (53), rubber plantation (82), mangosteen (29), and coconut (22). Additionally, samples were gathered for urban (61), water (40), forest (33), grass/shrub (39), bare ground (51), and others (76).…”

“…To date, most studies have focused on identifying individual crop types, such as sugarcane [43], mung bean [44], and paddy rice [45], with reported accuracies typically higher than 90%. Some other studies have attempted to map multiple, but limited numbers of, crop types (equal to or fewer than five) in one modeling framework (e.g., [46][47][48]). The reported accuracies were typically lower than mapping one single crop type, due to the similarity in phenology among the studied crops, making inter-class variation challenging to capture.…”

Crop Type Identification Using High-Resolution Remote Sensing Images Based on an Improved DeepLabV3+ Network

“…The prior studies have demonstrated that incorporating vegetation features into the extraction of crop distribution information from remote sensing imagery can result in improved discrimination between vegetation and non-vegetation, as well as different types of vegetation, compared to relying solely on the original four spectral bands [36][37][38]. This study employed prior knowledge to extract four additional vegetation indices from the original four spectral bands, namely the Normalized Difference Vegetation Index (NDVI), Green Normalized Difference Vegetation Index (GNDVI), Optimal Soil Adjusted Vegetation Index (OSAVI), and Canola Index (CI) [17,39].…”

Research on Red Jujubes Recognition Based on a Convolutional Neural Network

“…Chandel et al [12] found that the combination of computer vision and thermal RGB images helped in the high-throughput mitigation and management of crop water stress. The method proposed by Khan et al [13] can be applied on a large scale to effectively map the crop types of smallholder farms at an early stage, enabling them to plan a seamless supply of food. There are also studies that use different methods to study the same crop.…”