Identifying crop water stress using deep learning models
- PDF / 2,922,397 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 0 Downloads / 213 Views
(0123456789().,-volV)(0123456789(). ,- volV)
ORIGINAL ARTICLE
Identifying crop water stress using deep learning models Narendra Singh Chandel1 • Subir Kumar Chakraborty1 • Yogesh Anand Rajwade1 • Kumkum Dubey1 Mukesh K. Tiwari2 • Dilip Jat1
•
Received: 4 April 2020 / Accepted: 2 September 2020 Ó Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract The identification of water stress is a major challenge for timely and effective irrigation to ensure global food security and sustainable agriculture. Several direct and indirect methods exist for identification of crop water stress, but they are time consuming, tedious and require highly sophisticated sensors or equipment. Image processing is one of the techniques which can help in the assessment of water stress directly. Machine learning techniques combined with image processing can aid in identifying water stress beyond the limitations of traditional image processing. Deep learning (DL) techniques have gained momentum recently for image classification and the convolutional neural network based on DL is being applied widely. In present study, comparative assessment of three DL models: AlexNet, GoogLeNet and Inception V3 are applied for identification of water stress in maize (Zea mays), okra (Abelmoschus esculentus) and soybean (Glycine max) crops. A total of 1200 digital images were acquired for each crop to form the input dataset for the deep learning models. Among the three models, performance of GoogLeNet was found to be superior with an accuracy of 98.3, 97.5 and 94.1% for maize, okra and soybean, respectively. The onset of convergence in GoogLeNet models commenced after 8 epochs with 22 (maize), 31 (okra) and 15 (soybean) iterations per epoch with error rate of less than 7.5%. Keywords Crop phenotyping Confusion matrix DCNN Digital agriculture Machine learning
1 Introduction Environmentally sustainable solutions are required to double the global food production to feed the projected 9.1 billion population by 2050 [16]. Globally, natural resources such as land and water have been overexploited, degraded thus limiting the sustainable food production. Further, several challenges such as climate change, irregular occurrence and distribution of rainfall, heat stress, poor input use efficiency, etc. has rightfully aggravated the concerns [33]. Yield losses up to 90% have been reported by various researchers in major food crops due to abiotic stress such as drought and heat stress [14]. Drought stress is insufficient availability of soil moisture due to insufficient
& Mukesh K. Tiwari [email protected] 1
ICAR-Central Institute of Agricultural Engineering, Bhopal, India
2
College of Agricultural Engineering and Technology, Anand Agricultural University, Godhra, Gujarat, India
irrigation and/or rainfall such that it hampers evapotranspiration and induces physiological changes in crop affecting growth and yield [32, 44, 47]. Laboratory-based estimation of crop water stress is carried out by destructive methods by measuring leaf water pot
Data Loading...
