Smart Indoor Farms: Leveraging Technological Advancements to Power a Sustainable Agricultural Revolution

Applications of optical sensing and imaging spectroscopy in indoor farming: A systematic review

As demand for food continues to rise, innovative methods are needed to sustainably and efficiently meet the growing pressure on agriculture. Indoor farming and controlled environment agriculture have emerged as promising approaches to address this challenge. However, optimizing fertilizer usage, ensuring homogeneous production, and reducing agro-waste remain substantial challenges in these production systems. One potential solution is the use of optical sensing technology, which can provide real-time data to help growers make informed decisions and enhance their operations. optical sensing can be used to analyze plant tissues, evaluate crop quality and yield, measure nutrients, and assess plant responses to stress. This paper presents a systematic literature review of the current state of using spectral-optical sensors and hyperspectral imaging for indoor farming, following the PRISMA 2020 guidelines. The study surveyed existing studies from 2017 to 2023 to identify gaps in knowledge, provide researchers and farmers with current trends, and offer recommendations and inspirations for possible new research directions. The results of this review will contribute to the development of sustainable and efficient methods of food production.

Development of a machine vision-based weight prediction system of butterhead lettuce (Lactuca sativa L.) using deep learning models for industrial plant factory

Introduction

Indoor agriculture, especially plant factories, becomes essential because of the advantages of cultivating crops yearly to address global food shortages. Plant factories have been growing in scale as commercialized. Developing an on-site system that estimates the fresh weight of crops non-destructively for decision-making on harvest time is necessary to maximize yield and profits. However, a multi-layer growing environment with on-site workers is too confined and crowded to develop a high-performance system.This research developed a machine vision-based fresh weight estimation system to monitor crops from the transplant stage to harvest with less physical labor in an on-site industrial plant factory.

Methods

A linear motion guide with a camera rail moving in both the x-axis and y-axis directions was produced and mounted on a cultivating rack with a height under 35 cm to get consistent images of crops from the top view. Raspberry Pi4 controlled its operation to capture images automatically every hour. The fresh weight was manually measured eleven times for four months to use as the ground-truth weight of the models. The attained images were preprocessed and used to develop weight prediction models based on manual and automatic feature extraction.

Results and discussion

The performance of models was compared, and the best performance among them was the automatic feature extraction-based model using convolutional neural networks (CNN; ResNet18). The CNN-based model on automatic feature extraction from images performed much better than any other manual feature extraction-based models with 0.95 of the coefficients of determination (R2) and 8.06 g of root mean square error (RMSE). However, another multiplayer perceptron model (MLP_2) was more appropriate to be adopted on-site since it showed around nine times faster inference time than CNN with a little less R2 (0.93). Through this study, field workers in a confined indoor farming environment can measure the fresh weight of crops non-destructively and easily. In addition, it would help to decide when to harvest on the spot.

Agriculture 4.0: Polymer Hydrogels as Delivery Agents of Active Ingredients

The evolution from conventional to modern agricultural practices, characterized by Agriculture 4.0 principles such as the application of innovative materials, smart water, and nutrition management, addresses the present-day challenges of food supply. In this context, polymer hydrogels have become a promising material for enhancing agricultural productivity due to their ability to retain and then release water, which can help alleviate the need for frequent irrigation in dryland environments. Furthermore, the controlled release of fertilizers by the hydrogels decreases chemical overdosing risks and the environmental impact associated with the use of agrochemicals. The potential of polymer hydrogels in sustainable agriculture and farming and their impact on soil quality is revealed by their ability to deliver nutritional and protective active ingredients. Thus, the impact of hydrogels on plant growth, development, and yield was discussed. The question of which hydrogels are more suitable for agriculture-natural or synthetic-is debatable, as both have their merits and drawbacks. An analysis of polymer hydrogel life cycles in terms of their initial material has shown the advantage of bio-based hydrogels, such as cellulose, lignin, starch, alginate, chitosan, and their derivatives and hybrids, aligning with sustainable practices and reducing dependence on non-renewable resources.

A CNN-based model to count the leaves of rosette plants (LC-Net)

Plant image analysis is a significant tool for plant phenotyping. Image analysis has been used to assess plant trails, forecast plant growth, and offer geographical information about images. The area segmentation and counting of the leaf is a major component of plant phenotyping, which can be used to measure the growth of the plant. Therefore, this paper developed a convolutional neural network-based leaf counting model called LC-Net. The original plant image and segmented leaf parts are fed as input because the segmented leaf part provides additional information to the proposed LC-Net. The well-known SegNet model has been utilised to obtain segmented leaf parts because it outperforms four other popular Convolutional Neural Network (CNN) models, namely DeepLab V3+, Fast FCN with Pyramid Scene Parsing (PSP), U-Net, and Refine Net. The proposed LC-Net is compared to the other recent CNN-based leaf counting models over the combined Computer Vision Problems in Plant Phenotyping (CVPPP) and KOMATSUNA datasets. The subjective and numerical evaluations of the experimental results demonstrate the superiority of the LC-Net to other tested models.

A pilot study on non-invasive in situ detection of phytochemicals and plant endogenous status using fiber optic infrared spectroscopy

Traditional methods for assessing plant health often lack the necessary attributes for continuous and non-destructive monitoring. In this pilot study, we present a novel technique utilizing a customized fiber optic probe based on attenuated total reflection Fourier transform infrared spectroscopy (ATR-FTIR) with a contact force control unit for non-invasive and continuous plant health monitoring. We also developed a normalized difference mid-infrared reflectance index through statistical analysis of spectral features, enabling differentiation of drought and age conditions in plants. Our research aims to characterize phytochemicals and plant endogenous status optically, addressing the need for improved analytical measurement methods for in situ plant health assessment. The probe configuration was optimized with a triple-loop tip and a 3 N contact force, allowing sensitive measurements while minimizing leaf damage. By combining polycrystalline and chalcogenide fiber probes, a comprehensive wavenumber range analysis (4000-900 cm-1) was achieved. Results revealed significant variations in phytochemical composition among plant species, for example, red spinach with the highest polyphenolic content and green kale with the highest lignin content. Petioles displayed higher lignin and cellulose absorbance values compared to veins. The technique effectively monitored drought stress on potted green bok choy plants in situ, facilitating the quantification of changes in water content, antioxidant activity, lignin, and cellulose levels. This research represents the first demonstration of the potential of fiber optic ATR-FTIR probes for non-invasive and rapid plant health measurements, providing insights into plant health and advancements in quantitative monitoring for indoor farming practices, bioanalytical chemistry, and environmental sciences.

IoT-Based Monitoring System Applied to Aeroponics Greenhouse

The inclusion of the Internet of Things (IoT) in greenhouses has become a fundamental tool for improving cultivation systems, offering information relevant to the greenhouse manager for decision making in search of optimum yield. This article presents a monitoring system applied to an aeroponic greenhouse based on an IoT architecture that provides user information on the status of the climatic variables and the appearance of the crop in addition to managing the irrigation timing and the frequency of visual inspection using an application developed for Android mobile devices called Aeroponics Monitor. The proposed IoT architecture consists of four layers: a device layer, fog layer, cloud layer and application layer. Once the information about the monitored variables is obtained by the sensors of the device layer, the fog layer processes it and transfers it to the Thingspeak and Firebase servers. In the cloud layer, Thingspeak analyzes the information from the variables monitored in the greenhouse through its IoT analytic tools to generate historical data and visualizations of their behavior, as well as an analysis of the system’s operating status. Firebase, on the other hand, is used as a database to store the results of the processing of the images taken in the fog layer for the supervision of the leaves and roots. The results of the analysis of the information of the monitored variables and of the processing of the images are presented in the developed app, with the objective of visualizing the state of the crop and to know the function of the monitoring system in the event of a possible lack of electricity or a service line failure in the fog layer and to avoid the loss of information. With the information about the temperature of the plant leaf and the relative humidity inside the greenhouse, the vapor pressure deficit (VPD) in the cloud layer is calculated; the VPD values are available on the Thingspeak server and in the developed app. Additionally, an analysis of the VPD is presented that demonstrates a water deficiency from the transplanting of the seedling to the cultivation chamber. The IoT architecture presented in this paper represents a potential tool for the study of aeroponic farming systems through IoT-assisted monitoring.