Applications of Artificial Neural Networks in Greenhouse Technology and Overview for Smart Agriculture Development

AgriGAN: unpaired image dehazing via a cycle-consistent generative adversarial network for the agricultural plant phenotype

Artificially extracted agricultural phenotype information exhibits high subjectivity and low accuracy, while the utilization of image extraction information is susceptible to interference from haze. Furthermore, the effectiveness of the agricultural image dehazing method used for extracting such information is limited due to unclear texture details and color representation in the images. To address these limitations, we propose AgriGAN (unpaired image dehazing via a cycle-consistent generative adversarial network) for enhancing the dehazing performance in agricultural plant phenotyping. The algorithm incorporates an atmospheric scattering model to improve the discriminator model and employs a whole-detail consistent discrimination approach to enhance discriminator efficiency, thereby accelerating convergence towards Nash equilibrium state within the adversarial network. Finally, by training with network adversarial loss + cycle consistent loss, clear images are obtained after dehazing process. Experimental evaluations and comparative analysis were conducted to assess this algorithm's performance, demonstrating improved accuracy in dehazing agricultural images while preserving detailed texture information and mitigating color deviation issues.

A novel stochastic resonance based deep residual network for fault diagnosis of rolling bearing system

Rolling bearings constitute one of the most vital components in mechanical equipment, monitoring and diagnosing the condition of rolling bearings is essential to ensure safe operation. In actual production, the collected fault signals typically contain noise and cannot be accurately identified. In the paper, stochastic resonance (SR) is introduced into a spiking neural network (SNN) as a feature enhancement method for fault signals with varying noise intensities, combining deep learning with SR to enhance classification accuracy. The output signal-to-noise ratio(SNR) can be enhanced with the SR effect when the noise-affected fault signal input into neurons. Validation of the method is carried out through experiments on the CWRU dataset, achieving classification accuracy of 99.9%. In high-noise environments, with SNR equal to -8 dB, SRDNs achieve over 92% accuracy, exhibiting better robustness and adaptability.

Harnessing deep learning to forecast local microclimate using global climate data

Microclimate is a complex non-linear phenomenon influenced by both global and local processes. Its understanding holds a pivotal role in the management of natural resources and the optimization of agricultural procedures. This phenomenon can be effectively monitored in local areas by employing models that integrate physical laws and data-driven algorithms relying on climate data and terrain conformation. Climate data can be acquired from nearby meteorological stations when available, but in their absence, global climate datasets describing 10 km-scale areas are often utilized. The present research introduces an innovative microclimate model that combines physical laws and deep learning to reproduce temperature and relative humidity variations at the meter-scale within a study area located in the Lombardian foothills. The model is exploited to perform a comparative study investigating whether employing the global climate dataset ERA5 as input reduces model's accuracy in reproducing the microclimate variations compared to using data collected by the Lombardy Regional Environment Protection Agency (ARPA) from a nearby meteorological station. The comparative analysis shows that using local meteorological data as inputs provides more accurate results for microclimate modeling. However, in situations where local data is not available, the use of global climate data remains a viable and reliable approach.

Performance Analysis of Time Series Deep Learning Models for Climate Prediction in Indoor Hydroponic Greenhouses at Different Time Intervals

Indoor hydroponic greenhouses are becoming increasingly popular for sustainable food production. On the other hand, precise control of the climate conditions inside these greenhouses is crucial for the success of the crops. Time series deep learning models are adequate for climate predictions in indoor hydroponic greenhouses, but a comparative analysis of these models at different time intervals is needed. This study evaluated the performance of three commonly used deep learning models for climate prediction in an indoor hydroponic greenhouse: Deep Neural Network, Long-Short Term Memory (LSTM), and 1D Convolutional Neural Network. The performance of these models was compared at four time intervals (1, 5, 10, and 15 min) using a dataset collected over a week at one-minute intervals. The experimental results showed that all three models perform well in predicting the temperature, humidity, and CO₂ concentration in a greenhouse. The performance of the models varied at different time intervals, with the LSTM model outperforming the other models at shorter time intervals. Increasing the time interval from 1 to 15 min adversely affected the performance of the models. This study provides insights into the effectiveness of time series deep learning models for climate predictions in indoor hydroponic greenhouses. The results highlight the importance of choosing the appropriate time interval for accurate predictions. These findings can guide the design of intelligent control systems for indoor hydroponic greenhouses and contribute to the advancement of sustainable food production.

Prediction of cooling effect of constant temperature community bin based on BP neural network

In order to explore the influence of outdoor microclimate on the cooling effect of constant temperature community bin, the temperature prediction model was predicted. The temperature and microclimate data sets of the community bin were collected in summer from May 2021 to September 2021. The climatic characteristics included cloudy and sunny conditions, and the environmental factors included outdoor temperature, air speed, air relative humidity, and solar radiation intensity. Stepwise regression method was used to test the significance of environmental factors, and the corresponding regression equation was obtained. BP neural network was used to establish temperature prediction models under cloudy and sunny conditions, respectively. The results showed that the coefficient of determination (R²) of the two models was above 0.8, and the environmental factors with significant influence were screened out. The root mean square error (RMSE) between the training value and the actual value established by BP neural network was 0.83 °C, and the determination coefficient (R²) was 0.968. Under sunny conditions, the root mean square error (RMSE) of predicted value and measured value was 0.65 °C, and the determination coefficient (R²) was 0.982. According to the analysis of the sample data, it showed that the BP neural network was more accurate than stepwise regression, and could be used to predict the temperature of community bin, which provided model basis for the practical application of intelligent temperature control community bin in summer.

Machine Learning-Based Crop Stress Detection in Greenhouses

Greenhouse climate control systems are usually based on greenhouse microclimate settings to exert any control. However, to save energy, water and nutrients, additional parameters related to crop performance and physiology will have to be considered. In addition, detecting crop stress before it is clearly visible by naked eye is an advantage that could aid in microclimate control. In this study, a Machine Learning (ML) model which takes into account microclimate and crop physiological data to detect different types of crop stress was developed and tested. For this purpose, a multi-sensor platform was used to record tomato plant physiological characteristics under different fertigation and air temperature conditions. The innovation of the current model lies in the integration of photosynthesis rate (Ps) values estimated by means of remote sensing using a photochemical reflectance index (PRI). Through this process, the time-series Ps data were combined with crop leaf temperature and microclimate data by means of the ML model. Two different algorithms were evaluated: Gradient Boosting (GB) and MultiLayer perceptron (MLP). Two runs with different structures took place for each algorithm. In RUN 1, there were more feature inputs than the outputs to build a model with high predictive accuracy. However, in order to simplify the process and develop a user-friendly approach, a second, different run was carried out. Thus, in RUN 2, the inputs were fewer than the outputs, and that is why the performance of the model in this case was lower than in the case of RUN 1. Particularly, MLP showed 91% and 83% accuracy in the training sample, and 89% and 82% in testing sample, for RUNs 1 and 2, respectively. GB showed 100% accuracy in the training sample for both runs, and 91% and 83% in testing sample in RUN 1 and RUN 2, respectively. To improve the accuracy of RUN 2, a larger database is required. Both models, however, could easily be incorporated into existing greenhouse climate monitoring and control systems, replacing human experience in detecting greenhouse crop stress conditions.

An Intelligent Rice Yield Trait Evaluation System Based on Threshed Panicle Compensation

High-throughput phenotyping of yield-related traits is meaningful and necessary for rice breeding and genetic study. The conventional method for rice yield-related trait evaluation faces the problems of rice threshing difficulties, measurement process complexity, and low efficiency. To solve these problems, a novel intelligent system, which includes an integrated threshing unit, grain conveyor-imaging units, threshed panicle conveyor-imaging unit, and specialized image analysis software has been proposed to achieve rice yield trait evaluation with high throughput and high accuracy. To improve the threshed panicle detection accuracy, the Region of Interest Align, Convolution Batch normalization activation with Leaky Relu module, Squeeze-and-Excitation unit, and optimal anchor size have been adopted to optimize the Faster-RCNN architecture, termed 'TPanicle-RCNN,' and the new model achieved F1 score 0.929 with an increase of 0.044, which was robust to indica and japonica varieties. Additionally, AI cloud computing was adopted, which dramatically reduced the system cost and improved flexibility. To evaluate the system accuracy and efficiency, 504 panicle samples were tested, and the total spikelet measurement error decreased from 11.44 to 2.99% with threshed panicle compensation. The average measuring efficiency was approximately 40 s per sample, which was approximately twenty times more efficient than manual measurement. In this study, an automatic and intelligent system for rice yield-related trait evaluation was developed, which would provide an efficient and reliable tool for rice breeding and genetic research.

Feature Selection to Predict LED Light Energy Consumption with Specific Light Recipes in Closed Plant Production Systems

The use of closed growth environments, such as greenhouses, plant factories, and vertical farms, represents a sustainable alternative for fresh food production. Closed plant production systems (CPPSs) allow growing of any plant variety, no matter the year’s season. Artificial lighting plays an essential role in CPPSs as it promotes growth by providing optimal conditions for plant development. Nevertheless, it is a model with a high demand for electricity, which is required for artificial radiation systems to enhance the developing plants. A high percentage (40% to 50%) of the costs in CPPSs point to artificial lighting systems. Due to this, lighting strategies are essential to improve sustainability and profitability in closed plant production systems. However, no tools have been applied in the literature to contribute to energy savings in LED-type artificial radiation systems through the configuration of light recipes (wavelengths combination. For CPPS to be cost-effective and sustainable, a pre-evaluation of energy consumption for plant cultivation must consider. Artificial intelligence (AI) methods integrated into the prediction crucial variables such as each input-variable light color or specific wavelengths like red, green, blue, and white along with light intensity (quantity), frequency (pulsed light), and duty cycle. This paper focuses on the feature-selection stage, in which a regression model is trained to predict energy consumption in LED lights with specific light recipes in CPPSs. This stage is critical because it identifies the most representative features for training the model, and the other stages depend on it. These tools can enable further in-depth analysis of the energy savings that can be obtained with light recipes and pulsed and continuous operation light modes in artificial LED lighting systems.

Internet of Things Approaches for Monitoring and Control of Smart Greenhouses in Industry 4.0

In recent decades, climate change and a shortage of resources have brought about the need for technology in agriculture. Farmers have been forced to use information and innovation in communication in order to enhance production efficiency and crop resilience. Systems engineering and information infrastructure based on the Internet of Things (IoT) are the main novel approaches that have generated growing interest. In agriculture, IoT solutions according to the challenges for Industry 4.0 can be applied to greenhouses. Greenhouses are protected environments in which best plant growth can be achieved. IoT for smart greenhouses relates to sensors, devices, and information and communication infrastructure for real-time monitoring and data collection and processing, in order to efficiently control indoor parameters such as exposure to light, ventilation, humidity, temperature, and carbon dioxide level. This paper presents the current state of the art in the IoT-based applications to smart greenhouses, underlining benefits and opportunities of this technology in the agriculture environment.

A Deep Learning-Based Model for Date Fruit Classification

A total of 8.46 million tons of date fruit are produced annually around the world. The date fruit is considered a high-valued confectionery and fruit crop. The hot arid zones of Southwest Asia, North Africa, and the Middle East are the major producers of date fruit. The production of dates in 1961 was 1.8 million tons, which increased to 2.8 million tons in 1985. In 2001, the production of dates was recorded at 5.4 million tons, whereas recently it has reached 8.46 million tons. A common problem found in the industry is the absence of an autonomous system for the classification of date fruit, resulting in reliance on only the manual expertise, often involving hard work, expense, and bias. Recently, Machine Learning (ML) techniques have been employed in such areas of agriculture and fruit farming and have brought great convenience to human life. An automated system based on ML can carry out the fruit classification and sorting tasks that were previously handled by human experts. In various fields, CNNs (convolutional neural networks) have achieved impressive results in image classification. Considering the success of CNNs and transfer learning in other image classification problems, this research also employs a similar approach and proposes an efficient date classification model. In this research, a dataset of eight different classes of date fruit has been created to train the proposed model. Different preprocessing techniques have been applied in the proposed model, such as image augmentation, decayed learning rate, model checkpointing, and hybrid weight adjustment to increase the accuracy rate. The results show that the proposed model based on MobileNetV2 architecture has achieved 99% accuracy. The proposed model has also been compared with other existing models such as AlexNet, VGG16, InceptionV3, ResNet, and MobileNetV2. The results prove that the proposed model performs better than all other models in terms of accuracy.

The Influence of Genetic Algorithms on Learning Possibilities of Artificial Neural Networks

The presented research study focuses on demonstrating the learning ability of a neural network using a genetic algorithm and finding the most suitable neural network topology for solving a demonstration problem. The network topology is significantly dependent on the level of generalization. More robust topology of a neural network is usually more suitable for particular details in the training set and it loses the ability to abstract general information. Therefore, we often design the network topology by taking into the account the required generalization, rather than the aspect of theoretical calculations. The next part of the article presents research whether a modification of the parameters of the genetic algorithm can achieve optimization and acceleration of the neural network learning process. The function of the neural network and its learning by using the genetic algorithm is demonstrated in a program for solving a computer game. The research focuses mainly on the assessment of the influence of changes in neural networks’ topology and changes in parameters in genetic algorithm on the achieved results and speed of neural network training. The achieved results are statistically presented and compared depending on the network topology and changes in the learning algorithm.

Joint Communication and Sensing: A Proof of Concept and Datasets for Greenhouse Monitoring Using LoRaWAN

In recent years, greenhouse-based precision agriculture (PA) has been strengthened by utilization of Internet of Things applications and low-power wide area network communication. The advancements in multidisciplinary technologies such as artificial intelligence (AI) have created opportunities to assist farmers further in detecting disease and poor nutrition of plants. Neural networks and other AI techniques need an initial set of measurement campaigns along with extensive datasets as a training set to baseline and evolve different applications. This paper presents LoRaWAN-based greenhouse monitoring datasets over a period of nine months. The dataset has both the network and sensing information from multiple sensor nodes for tomato crops in two different greenhouse environments. The goal is to provide the research community with a dataset to evaluate performance of LoRaWAN inside a greenhouse and develop more efficient PA monitoring techniques. In this paper, we carried out an exploratory data analysis to infer crop growth by analyzing just the LoRaWAN signals and without inclusion of any extra hardware. This work uses a multilayer perceptron artificial neural network to predict the weekly plant growth, trained using RSSI value from sensor data and manual measurement of plant height from the greenhouse. We developed this proof of concept of joint communication and sensing by using generated dataset from the “Proefcentrum Hoogstraten” greenhouse in Belgium. Results for the proposed method yield a root mean square error of 10% in detecting the average plant height inside a greenhouse. In future, we can use this concept of landscape sensing for different supplementary use-cases and to develop optimized methods.

A Machine Learning Based Model for Energy Usage Peak Prediction in Smart Farms

Context: Energy utilization is one of the most closely related factors affecting many areas of the smart farm, plant growth, crop production, device automation, and energy supply to the same degree. Recently, 4th industrial revolution technologies such as IoT, artificial intelligence, and big data have been widely used in smart farm environments to efficiently use energy and control smart farms’ conditions. In particular, machine learning technologies with big data analysis are actively used as one of the most potent prediction methods supporting energy use in the smart farm. Purpose: This study proposes a machine learning-based prediction model for peak energy use by analyzing energy-related data collected from various environmental and growth devices in a smart paprika farm of the Jeonnam Agricultural Research and Extension Service in South Korea between 2019 and 2021. Scientific method: To find out the most optimized prediction model, comparative evaluation tests are performed using representative ML algorithms such as artificial neural network, support vector regression, random forest, K-nearest neighbors, extreme gradient boosting and gradient boosting machine, and time series algorithm ARIMA with binary classification for a different number of input features. Validate: This article can provide an effective and viable way for smart farm managers or greenhouse farmers who can better manage the problem of agricultural energy economically and environmentally. Therefore, we hope that the recommended ML method will help improve the smart farm’s energy use or their energy policies in various fields related to agricultural energy. Conclusion: The seven performance metrics including R-squared, root mean squared error, and mean absolute error, are associated with these two algorithms. It is concluded that the RF-based model is more successful than in the pre-others diction accuracy of 92%. Therefore, the proposed model may be contributed to the development of various applications for environment energy usage in a smart farm, such as a notification service for energy usage peak time or an energy usage control for each device.

Ensuring Agricultural Sustainability through Remote Sensing in the Era of Agriculture 5.0

Timely and reliable information about crop management, production, and yield is considered of great utility by stakeholders (e.g., national and international authorities, farmers, commercial units, etc.) to ensure food safety and security. By 2050, according to Food and Agriculture Organization (FAO) estimates, around 70% more production of agricultural products will be needed to fulfil the demands of the world population. Likewise, to meet the Sustainable Development Goals (SDGs), especially the second goal of “zero hunger”, potential technologies like remote sensing (RS) need to be efficiently integrated into agriculture. The application of RS is indispensable today for a highly productive and sustainable agriculture. Therefore, the present study draws a general overview of RS technology with a special focus on the principal platforms of this technology, i.e., satellites and remotely piloted aircrafts (RPAs), and the sensors used, in relation to the 5th industrial revolution. Nevertheless, since 1957, RS technology has found applications, through the use of satellite imagery, in agriculture, which was later enriched by the incorporation of remotely piloted aircrafts (RPAs), which is further pushing the boundaries of proficiency through the upgrading of sensors capable of higher spectral, spatial, and temporal resolutions. More prominently, wireless sensor technologies (WST) have streamlined real time information acquisition and programming for respective measures. Improved algorithms and sensors can, not only add significant value to crop data acquisition, but can also devise simulations on yield, harvesting and irrigation periods, metrological data, etc., by making use of cloud computing. The RS technology generates huge sets of data that necessitate the incorporation of artificial intelligence (AI) and big data to extract useful products, thereby augmenting the adeptness and efficiency of agriculture to ensure its sustainability. These technologies have made the orientation of current research towards the estimation of plant physiological traits rather than the structural parameters possible. Futuristic approaches for benefiting from these cutting-edge technologies are discussed in this study. This study can be helpful for researchers, academics, and young students aspiring to play a role in the achievement of sustainable agriculture.

Forecasting Air Temperature on Edge Devices with Embedded AI

With the advent of the Smart Agriculture, the joint utilization of Internet of Things (IoT) and Machine Learning (ML) holds the promise to significantly improve agricultural production and sustainability. In this paper, the design of a Neural Network (NN)-based prediction model of a greenhouse's internal air temperature, to be deployed and run on an edge device with constrained capabilities, is investigated. The model relies on a time series-oriented approach, taking as input variables the past and present values of the air temperature to forecast the future ones. In detail, we evaluate three different NN architecture types-namely, Long Short-Term Memory (LSTM) networks, Recurrent NNs (RNNs) and Artificial NNs (ANNs)-with various values of the sliding window associated with input data. Experimental results show that the three best-performing models have a Root Mean Squared Error (RMSE) value in the range 0.289÷0.402∘C, a Mean Absolute Percentage Error (MAPE) in the range of 0.87÷1.04%, and a coefficient of determination (R2) not smaller than 0.997. The overall best performing model, based on an ANN, has a good prediction performance together with low computational and architectural complexities (evaluated on the basis of the NetScore metric), making its deployment on an edge device feasible.

Development of Technological Capabilities through the Internet of Things (IoT): Survey of Opportunities and Barriers for IoT Implementation in Portugal’s Agro-Industry

The agro-industrial sector consumes a significant amount of natural resources for farming and meat production. By 2050, population growth is expected, generating more demand and, consequently, more consumption of scarce resources. This challenging scenario is a concern of the European Commission, revealed in the Green Deal commitment and by the United Nations’ 12th goal of sustainable development. Thus, organizations must increase productivity and be more sustainable as soon as possible. Internet of Things (IoT) is introduced as a solution to facilitate agro-food companies to be more eco-efficient, mainly facing difficulties on farms, such as food loss and waste, best efficiency in management of resources, and production. The deployment of this technology depends on the stage of maturity and potential of implementation. To assess and characterize companies, with respect of IoT implementation, a survey was applied in 21 micro, small and medium agro-food companies, belonging to milk, honey, olive oil, jams, fruticulture, bakery and pastry, meat, coffee, and wine sectors, in the central region of Portugal. As results, this paper reveals the stage of maturity, level of sophistication, potential, opportunities, solutions, and barriers for implementation of IoT. Additionally, suggestions and recommendations to improve practices are discussed.

Modeling Energy LED Light Consumption Based on an Artificial Intelligent Method Applied to Closed Plant Production System

Artificial lighting is a key factor in Closed Production Plant Systems (CPPS). A significant light-emitting diode (LED) technology attribute is the emission of different wavelengths, called light recipes. Light recipes are typically configured in continuous mode, but can also be configured in pulsed mode to save energy. We propose two nonlinear models, i.e., genetic programing (GP) and feedforward artificial neural networks (FNNs) to predict energy consumption in CPPS. The generated models use the following input variables: intensity, red light component, blue light component, green light component, and white light component; and the following operation modes: continuous and pulsed light including pulsed frequency, and duty cycle as well energy consumption as output. A Spearman’s correlation was applied to generate a model with only representative inputs. Two datasets were applied. The first (Test 1), with 5700 samples with similar input ranges, was used to train and evaluate, while the second (Test 2), included 160 total datapoints in different input ranges. The metrics that allowed a quantitative evaluation of the model’s performance were MAPE, MSE, MAE, and SEE. Our implemented models achieved an accuracy of 96.1% for the GP model and 98.99% for the FNNs model. The models used in this proposal can be applied or programmed as part of the monitoring system for CPPS which prioritize energy efficiency. The nonlinear models provide a further analysis for energy savings due to the light recipe and operation light mode, i.e., pulsed and continuous on artificial LED lighting systems.

Estimation of Free Fatty Acids in Stored Paddy Rice Using Multiple-Kernel Support Vector Regression

Grain quality changes during the storage period, and an important grain quality indictor is the free fatty acid (FFA) content. Understanding real-time change of FFA content in stored grain is significant for grain storage safety. However, the FFA content requires manual detection with time-consuming and complex procedures. Thus, this paper is dedicated to developing a method to estimate FFA content in stored grain accurately. We proposed a machine learning approach—multiple-kernel support vector regression—to complete this goal, which improved the accuracy and robustness of the FFA estimation. The effectiveness of the proposed approach was validated by the grain storage data collected from northeast China. To show the merits of the proposed method, several prevailing prediction methods, such as single-kernel support vector regression, multiple linear regression, and back propagation neural network, were introduced for comparative purposes, and several quantitative statistical indexes were adopted to evaluate the performance of different models. The results showed that the proposed approach can achieve a high accuracy with mean absolute error of 0.341 mg KOH/100 g, root mean square error of 0.442 mg KOH/100 g, and mean absolute percentage error of 2.026%. Among the four models tested, the multiple-kernel support vector regression model performed best and made the most robust forecasts of FFA content in stored grain.

Model Predictive Control of Smart Greenhouses as the Path towards Near Zero Energy Consumption

Modern agriculture represents an economic sector that can mainly benefit from technology innovation according to the principles suggested by Industry 4.0 for smart farming systems. Greenhouse industry is significantly becoming more and more technological and automatized to improve the quality and efficiency of crop production. Smart greenhouses are equipped with forefront IoT- and ICT-based monitoring and control systems. New remote sensors, devices, networking communication, and control strategies can make available real-time information about crop health, soil, temperature, humidity, and other indoor parameters. Energy efficiency plays a key role in this context, as a fundamental path towards sustainability of the production. This paper is a review of the precision and sustainable agriculture approaches focusing on the current advance technological solution to monitor, track, and control greenhouse systems to enhance production in a more sustainable way. Thus, we compared and analyzed traditional versus model predictive control methods with the aim to enhance indoor microclimate condition management under an energy-saving approach. We also reviewed applications of sustainable approaches to reach nearly zero energy consumption, while achieving nearly zero water and pesticide use.