A crop yield prediction model based on an improved artificial neural network and yield monitoring using a blockchain technique

Abstract

Nowadays, improving a crop yield ([Formula: see text]) is an emerging and essential task to reduce food scarcity. Factors impacting [Formula: see text] improvement include rising population, water shortage, fertilizer use, climate change and unprecedented insect attacks. To resolve these issues, a smart agriculture technique is proposed in this work. Internet of Things (IoT) sensor devices are used to collect data from farms, following which the fuzzy association rule-based classification technique classifies the data into two, valuable and nonvaluable. An improved artificial neural network (IANN) algorithm is applied to identify and analyze the factors involved in monitoring [Formula: see text]’s. Thereafter, all valuable data pertaining to the type of seed, fertilizer and crop cost is stored in blocks to secure data and communication between members of the farming community. Finally, an edge computing device is used to store the blocks and transfer information. The valuable data collected is classified using the fuzzy association rule and analyzed using the IANN technique, both of which facilitate a comparison with the historical data so as to enable better decision making in terms of seed and fertilizer selection. Similarly, crop price is predicted through a comparison of present and historical yields. To overcome breaches in security, a blockchain technique is employed in this work to secure communication between farmers, investors and merchants. The investor dispatches instructions on the selection of the seed and fertilizer, as well as the crop cost, through the blockchain to the farmer and the merchant. Such secure communication bypasses third-party involvement and inconsistencies in the data. When compared to the traditional method, the proposed technique offers better accuracy and profits, right from seed selection to trading. The proposed IANN technique produced a higher yield than the traditional method with a profit of 51%, 35% and 20% for rice, bananas and flowers, respectively. Similarly, the IANN technique provides 99.15% prediction accuracy in terms of a profit analysis. The blockchain and edge computing-based transactions improve security and reduce transactional latency. The proposed system ensures sustainability and traceability in agriculture.

Blockchain-Based Traceability for Agricultural Products: A Systematic Literature Review

“…A crop monitoring and classification system based on the IoT is proposed for automatic sensing, storage and monitoring of real-time parameters, which have an important impact on the quality and yield of crops [155]. In order to increase crop yields and secure all the valuable data related to seed type, fertilizer and crop costs, a smart agriculture technique is proposed [156]. IoT sensor devices are used to collect data from farms, crop yield predictions are realized based on machine learning algorithms, and all valuable data related to seed types, fertilizers and crop costs are stored in blocks to secure the security of the data and communication.…”