Deep Learning Agricultural Application

Agriculture benefits from AI, particularly, with the advancements in deep learning (DL) concepts, significant improvements have been observed in agricultural.

The ability of …

Feb. 23, 2022 5 minute
Deep Learning Agricultural Application,Deep Learning

Description :

Agriculture benefits from AI, particularly, with the advancements in deep learning (DL) concepts, significant improvements have been observed in agricultural.

The ability of automatic feature extraction creates an adaptive nature in deep learning (DL).  Convolutional neural networks which has strong image processing capabilities improve accuracy in various agricultural applications, such as plant disease detection and classification, weed/crop discrimination, fruit counting, land cover classification, and crop/plant recognition.

The analysis of prominent studies highlighted that the DL-based models, like RCNN (Region-based Convolutional Neural Network), achieve a higher plant disease/pest detection rate (82.51%) than the well-known ML algorithms, like K-nearest Neighbor (63.76%). The famous DL architecture named ResNet-18 attained more accurate Area Under the Curve (94.84%), and outperformed ML-based techniques, including Random Forest (RF) (70.16%) and Support Vector Machine (SVM) (60.6%), for crop/weed discrimination. Another DL model called FCN (Fully Convolutional Networks) recorded higher accuracy (83.9%) than SVM (67.6%) and RF (65.6%) algorithms for the classification of agricultural land covers. 

Research showed that the accuracy of a DL model in plant disease detection which employ leaf pattern recognition and image classification can go up to 95.8% after going through 100 iterations of training which can be further improved to reach 96.3% by more training. This indicates that DL outperforms manual plant disease detection.

Although deep learning significantly has changed the agriculture world, with great potential in deep learning, enormous improvements are on the way.