A low-cost AI-IoT integrated smart farming system with IoT sensor network simulation for Smallholder farms


Abstract

This study shows how to build, test, and put into use a low-cost, modular AI-IoT smart farming system that is perfect for smallholder farmers. The system uses Python-based sensor network simulation to imitate getting real-time data arising from sensors that measure soil moisture, temperature, humidity, light, pH, and the concentrations of nitrogen, phosphorus, and potassium in the soil. This cuts down on the requirement for costly hardware during development and training. Using edge computing on a Raspberry Pi with SQLite stored locally ensures that analytics occur in real-time, data is kept safe, and everything works well even when the internet is down. We created AI models, such as Random Forest classifiers and regressors, to check the health of plants, forecast how much they would produce, and find the best way to water them. We used both synthetic and real-world data for this. The system had 99.2% uptime, 98.6% data success rate, almost flawless AI accuracy, and low-latency inference (<200 ms) atop a 60-day field experiment. Economic analysis of scalable designs showed a quick return on investment (ROI of 2,079%–4,777%), and yearly benefits per hectare that are much higher than the original investment. This used to be due to yield increases of 15–25%, water savings of 20–30%, and labor cuts of around 30%. The system's modular, offline-capable design immediately solves problems with cost, technological complexity, and intermittent connection, which are common within rural areas. The results show that it is possible to make modern digital agricultural technologies available to everyone, giving smallholder farmers useful, data-driven information that will help them be more productive in the long term.
Ask to review this manuscript

Notes for potential reviewers

  • Volunteering is not a guarantee that you will be asked to review. There are many reasons: reviewers must be qualified, there should be no conflicts of interest, a minimum of two reviewers have already accepted an invitation, etc.
  • This is NOT OPEN peer review. The review is single-blind, and all recommendations are sent privately to the Academic Editor handling the manuscript. All reviews are published and reviewers can choose to sign their reviews.
  • What happens after volunteering? It may be a few days before you receive an invitation to review with further instructions. You will need to accept the invitation to then become an official referee for the manuscript. If you do not receive an invitation it is for one of many possible reasons as noted above.

  • PeerJ Computer Science does not judge submissions based on subjective measures such as novelty, impact or degree of advance. Effectively, reviewers are asked to comment on whether or not the submission is scientifically and technically sound and therefore deserves to join the scientific literature. Our Peer Review criteria can be found on the "Editorial Criteria" page - reviewers are specifically asked to comment on 3 broad areas: "Basic Reporting", "Experimental Design" and "Validity of the Findings".
  • Reviewers are expected to comment in a timely, professional, and constructive manner.
  • Until the article is published, reviewers must regard all information relating to the submission as strictly confidential.
  • When submitting a review, reviewers are given the option to "sign" their review (i.e. to associate their name with their comments). Otherwise, all review comments remain anonymous.
  • All reviews of published articles are published. This includes manuscript files, peer review comments, author rebuttals and revised materials.
  • Each time a decision is made by the Academic Editor, each reviewer will receive a copy of the Decision Letter (which will include the comments of all reviewers).

If you have any questions about submitting your review, please email us at [email protected].