Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Cost-Effective Cyber-Physical System Prototype for Precision Agriculture with a Focus on Crop Growth

Pawan Kumar, Hokeun Kim

TL;DR

This paper tackles the need for deployable, cost-effective cyber-physical systems in precision agriculture by presenting a rapid prototyping workflow that integrates sensors, image processing, and predictive modeling to non-destructively estimate leaf area and biomass. The prototype combines an ESP32-based controller, a DHT11 and an AS7341 sensor, a Raspberry Pi, a camera, and remote server analytics, achieving accurate leaf-area measurements primarily with the TF-Luna sensor. Growth prediction employs a power-function relationship analyzed via linear and Bayesian linear regression, both yielding strong explanatory power (R$^2$ > 0.90) and showing linear regression has a slight edge in MSE. The work demonstrates a cost-effective, scalable CPS blueprint (total hardware cost around $202.35) with clear paths for enhancements such as depth sensing and automated environmental control to boost sustainable crop yields.

Abstract

In precision agriculture, integrating advanced technologies is crucial for optimizing plant growth and health monitoring. Cyber-physical system (CPS) platforms tailored to specific agricultural environments have emerged, but the diversity of these environments poses challenges in developing adaptive CPS platforms. This paper explores rapid prototyping methods to address these challenges, focusing on non-destructive techniques for estimating plant growth. We present a CPS prototype that combines sensors, microcontrollers, digital image processing, and predictive modeling to measure leaf area and biomass accumulation in hydroponic environments. Our results show that the prototype effectively monitors and predicts plant growth, highlighting the potential of rapid CPS prototyping in promoting sustainability and improving crop yields at a moderate cost of hardware.

Cost-Effective Cyber-Physical System Prototype for Precision Agriculture with a Focus on Crop Growth

TL;DR

This paper tackles the need for deployable, cost-effective cyber-physical systems in precision agriculture by presenting a rapid prototyping workflow that integrates sensors, image processing, and predictive modeling to non-destructively estimate leaf area and biomass. The prototype combines an ESP32-based controller, a DHT11 and an AS7341 sensor, a Raspberry Pi, a camera, and remote server analytics, achieving accurate leaf-area measurements primarily with the TF-Luna sensor. Growth prediction employs a power-function relationship analyzed via linear and Bayesian linear regression, both yielding strong explanatory power (R > 0.90) and showing linear regression has a slight edge in MSE. The work demonstrates a cost-effective, scalable CPS blueprint (total hardware cost around $202.35) with clear paths for enhancements such as depth sensing and automated environmental control to boost sustainable crop yields.

Abstract

In precision agriculture, integrating advanced technologies is crucial for optimizing plant growth and health monitoring. Cyber-physical system (CPS) platforms tailored to specific agricultural environments have emerged, but the diversity of these environments poses challenges in developing adaptive CPS platforms. This paper explores rapid prototyping methods to address these challenges, focusing on non-destructive techniques for estimating plant growth. We present a CPS prototype that combines sensors, microcontrollers, digital image processing, and predictive modeling to measure leaf area and biomass accumulation in hydroponic environments. Our results show that the prototype effectively monitors and predicts plant growth, highlighting the potential of rapid CPS prototyping in promoting sustainability and improving crop yields at a moderate cost of hardware.
Paper Structure (12 sections, 4 equations, 9 figures, 6 tables)

This paper contains 12 sections, 4 equations, 9 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Related Work and Background
  3. Prototype Design and Implementation
  4. Prototype Design
  5. Hardware Components
  6. Hardware Prototype Design
  7. Crop Growth Estimation
  8. Crop Growth Prediction Model
  9. Evaluation
  10. Cost Evaluation
  11. Comparative Analysis of Modeling Approaches
  12. Conclusion and Future Work

Figures (9)

  • Figure 1: An overview of our prototype.
  • Figure 2: Hardware components diagram illustrating the setup of our prototype using ESP32, DHT11 and AS7341 with a legend represents the wire connections.
  • Figure 3: Support structure to hold the hardware components above the plant.
  • Figure 4: Internal hardware configuration consisting of Raspberry Pi CSRpi, camera CSRpiCam, and distance sensor, presented as (a) a 2D image, (b) a 3D image, and (c) an actual picture.
  • Figure 5: Distance sensor and camera placed close to each other to measure the distance and take images respectively presented as (a) a 2D image, (b) a 3D image, and (c) an actual picture.
  • ...and 4 more figures