Submit to Sensors Review for Sensors Propose a Special Issue

Journal Browser

► Journal Browser

Application of Artificial Neural Network and Sensing in Advanced Agriculture

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Internet of Things".

Deadline for manuscript submissions: closed (15 September 2022) | Viewed by 19023

Share This Special Issue

Special Issue Editors

Prof. Dr. José Miguel Molina Martínez

E-Mail Website
Guest Editor

Department of Agricultural Engineering, Technical University of Cartagena, 30202 Cartagena, Murcia, Spain
Interests: water resources management; irrigation; energy efficiency; smart agriculture; agriculture automation and control; computers and electronics in agriculture
Special Issues, Collections and Topics in MDPI journals

Dr. Luis Manuel Navas Gracia

E-Mail Website1 Website2
Guest Editor

Escuela Técnica Superior de Ingenierías Agrarias de Palencia, Universidad de Valladolid, 47004 Valladolid, Spain
Interests: renewable energies; energy efficiency; process automation; precision farming; greenhouse technology; waste reutilization; urban farming
Special Issues, Collections and Topics in MDPI journals

Prof. Dr. Manuel Ramiro Rodríguez Rodríguez

E-Mail Website
Guest Editor

Department of Agroforestry Engineering, University of Santiago de Compostela, 27002 Lugo, Spain
Interests: environmental and animal variables modeling and control; sustainability and energy efficiency; smart farming; agriculture monitoring; precision farming; livestock management; animal behavior; agriculture emissions
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Over the last few years, there has been a strong development of new technologies applied to the monitoring and control of different agricultural and livestock processes. This new growth has contributed to a significant increase in productivity, improvement in quality and animal welfare, as well as a reduction in environmental impact. In the coming years, due to the high growth expectations of smart farming, there will be an increase in sensors that offer real-time information and advanced data processing in different digital environments. The use of different artificial intelligence techniques in these advanced data processing activities is currently a reality.

The Special Edition of this publication is directed at these new sensing and processing data techniques for new agricultural production models, based on the use of sensors, information and communication technologies, and artificial neural networks, which will help to ensure a sustainable agriculture and that there is enough food to feed an increasing population.

Prof. Dr. José Miguel Molina Martínez
Dr. Luis Manuel Navas Gracia
Prof. Dr. Manuel Ramiro Rodríguez Rodríguez
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

smart farming
precision agriculture
Farming 4.0
agriculture monitoring
sensor technologies
Internet of Things
processing of data in agriculture
information and communication technology
artificial neural network
artificial intelligence

Published Papers (9 papers)

Download All Papers

Research

16 pages, 5455 KiB

Open AccessArticle

Using Aerial Thermal Imagery to Evaluate Water Status in Vitis vinifera cv. Loureiro

by Cláudio Araújo-Paredes, Fernando Portela, Susana Mendes and M. Isabel Valín

Sensors 2022, 22(20), 8056; https://0-doi-org.brum.beds.ac.uk/10.3390/s22208056 - 21 Oct 2022

Cited by 7 | Viewed by 1953

Abstract

The crop water stress index (CWSI) is a widely used analytical tool based on portable thermography. This method can be useful in replacing the traditional stem water potential method obtained with a Scholander chamber (PMS Model 600) because the latter is not feasible for large-scale studies due to the time involved and the fact that it is invasive and can cause damage to the plant. The present work had three objectives: (i) to understand if CWSI estimated using an aerial sensor can estimate the water status of the plant; (ii) to compare CWSI from aerial-thermographic and portable thermal cameras with stem water potential; (iii) to estimate the capacity of an unmanned aerial vehicle (UAV) to calculate and spatialize CWSI. Monitoring of CWSI (CWSI_P) using a portable device was performed directly in the canopy, by measuring reference temperatures (T_dry, T_wet, and canopy temperature (T_c)). Aerial CWSI calculation was performed using two models: (i) a simplified CWSI model (CWSI_S), where the T_dry and T_wet were estimated as the average of 1% of the extreme temperature, and (ii) an air temperature model (CWSI_Tair) where air temperatures (T_air + 7 °C) were recorded as T_dry and in the T_wet, considering the average of the lowest 33% of histogram values. In these two models, the T_c value corresponded to the temperature value in each pixel of the aerial thermal image. The results show that it was possible to estimate CWSI by calculating canopy temperatures and spatializing CWSI using aerial thermography. Of the two models, it was found that for CWSI_Tair, CWSI_S (R² = 0.55) evaluated crop water stress better than stem water potential. The CWSI_S had good correlation compared with the portable sensor (R² = 0.58), and its application in field measurements is possible. Full article

(This article belongs to the Special Issue Application of Artificial Neural Network and Sensing in Advanced Agriculture)

► Show Figures

Figure 1

22 pages, 6535 KiB

Open AccessArticle

Fast and Non-Destructive Quail Egg Freshness Assessment Using a Thermal Camera and Deep Learning-Based Air Cell Detection Algorithms for the Revalidation of the Expiration Date of Eggs

by Victor Massaki Nakaguchi and Tofael Ahamed

Sensors 2022, 22(20), 7703; https://0-doi-org.brum.beds.ac.uk/10.3390/s22207703 - 11 Oct 2022

Cited by 2 | Viewed by 2557

Abstract

Freshness is one of the most important parameters for assessing the quality of avian eggs. Available techniques to estimate the degradation of albumen and enlargement of the air cell are either destructive or not suitable for high-throughput applications. The aim of this research was to introduce a new approach to evaluate the air cell of quail eggs for freshness assessment as a fast, noninvasive, and nondestructive method. A new methodology was proposed by using a thermal microcamera and deep learning object detection algorithms. To evaluate the new method, we stored 174 quail eggs and collected thermal images 30, 50, and 60 days after the labeled expiration date. These data, 522 in total, were expanded to 3610 by image augmentation techniques and then split into training and validation samples to produce models of the deep learning algorithms, referred to as “You Only Look Once” version 4 and 5 (YOLOv4 and YOLOv5) and EfficientDet. We tested the models in a new dataset composed of 60 eggs that were kept for 15 days after the labeled expiration label date. The validation of our methodology was performed by measuring the air cell area highlighted in the thermal images at the pixel level; thus, we compared the difference in the weight of eggs between the first day of storage and after 10 days under accelerated aging conditions. The statistical significance showed that the two variables (air cell and weight) were negatively correlated (R² = 0.676). The deep learning models could predict freshness with F1 scores of 0.69, 0.89, and 0.86 for the YOLOv4, YOLOv5, and EfficientDet models, respectively. The new methodology for freshness assessment demonstrated that the best model reclassified 48.33% of our testing dataset. Therefore, those expired eggs could have their expiration date extended for another 2 weeks from the original label date. Full article

(This article belongs to the Special Issue Application of Artificial Neural Network and Sensing in Advanced Agriculture)

► Show Figures

Figure 1

13 pages, 2721 KiB

Open AccessArticle

Fusion of Different Image Sources for Improved Monitoring of Agricultural Plots

by Enrique Moltó

Sensors 2022, 22(17), 6642; https://0-doi-org.brum.beds.ac.uk/10.3390/s22176642 - 02 Sep 2022

Cited by 3 | Viewed by 1185

Abstract

In the Valencian Community, the applications of precision agriculture in multiannual woody crops with high added value (fruit trees, olive trees, almond trees, vineyards, etc.) are of priority interest. In these plots, canopies do not fully cover the soil and the planting frames are incompatible with the Resolution of Sentinel 2. The present work proposes a procedure for the fusion of images with different temporal and spatial resolutions and with different degrees of spectral quality. It uses images from the Sentinel 2 mission (low resolution, high spectral quality, high temporal resolution), orthophotos (high resolution, low temporal resolution) and images obtained with drones (very high spatial resolution, low temporal resolution). The procedure is applied to generate time series of synthetic RGI images (red, green, infrared) with the same high resolution of orthophotos and drone images, in which gray levels are reassigned from the combination of their own RGI bands and the values of the B3, B4 and B8 bands of Sentinel 2. Two practical examples of application are also described. The first shows the NDVI images that can be generated after the process of merging two RGI Sentinel 2 images obtained on two specific dates. It is observed how, after the merging, different NDVI values can be assigned to the soil and vegetation, which allows them to be distinguished (contrary to the original Sentinel 2 images). The second example shows how graphs can be generated to describe the evolution throughout the vegetative cycle of the estimated values of three spectral indices (NDVI, GNDVI, GCI) on a point in the image corresponding to soil and on another assigned to vegetation. The robustness of the proposed algorithm has been validated by using image similarity metrics. Full article

(This article belongs to the Special Issue Application of Artificial Neural Network and Sensing in Advanced Agriculture)

► Show Figures

Figure 1

21 pages, 3143 KiB

Open AccessArticle

Prediction of Daily Ambient Temperature and Its Hourly Estimation Using Artificial Neural Networks in an Agrometeorological Station in Castile and León, Spain

by Francisco J. Diez, Adriana Correa-Guimaraes, Leticia Chico-Santamarta, Andrés Martínez-Rodríguez, Diana A. Murcia-Velasco, Renato Andara and Luis M. Navas-Gracia

Sensors 2022, 22(13), 4850; https://0-doi-org.brum.beds.ac.uk/10.3390/s22134850 - 27 Jun 2022

Cited by 4 | Viewed by 1503

Abstract

This study evaluates the predictive modeling of the daily ambient temperature (maximum, T_max; average, T_ave; and minimum, T_min) and its hourly estimation (T_0h, …, T_23h) using artificial neural networks (ANNs) for agricultural applications. The data, 2004–2010, were used for training and 2011 for validation, recorded at the SIAR agrometeorological station of Mansilla Mayor (León). ANN models for daily prediction have three neurons in the output layer (T_max(t + 1), T_ave(t + 1), T_min(t + 1)). Two models were evaluated: (1) with three entries (T_max(t), T_ave(t), T_min(t)), and (2) adding the day of the year (J(t)). The inclusion of J(t) improves the predictions, with an RMSE for T_max = 2.56, T_ave = 1.65 and T_min = 2.09 (°C), achieving better results than the classical statistical methods (typical year T_ave = 3.64 °C; weighted moving mean T_max = 2.76, T_ave = 1.81 and T_min = 2.52 (°C); linear regression T_ave = 1.85 °C; and Fourier T_max = 3.75, T_ave = 2.67 and T_min = 3.34 (°C)) for one year. The ANN models for hourly estimation have 24 neurons in the output layer (T_0h(t), …, T_23h(t)) corresponding to the mean hourly temperature. In this case, the inclusion of the day of the year (J(t)) does not significantly improve the estimations, with an RMSE = 1.25 °C, but it improves the results of the ASHRAE method, which obtains an RMSE = 2.36 °C for one week. The results obtained, with lower prediction errors than those achieved with the classical methods, confirm the interest in using the ANN models for predicting temperatures in agricultural applications. Full article

(This article belongs to the Special Issue Application of Artificial Neural Network and Sensing in Advanced Agriculture)

► Show Figures

Figure 1

17 pages, 6423 KiB

Open AccessArticle

Alternate Wetting and Drying in the Center of Portugal: Effects on Water and Rice Productivity and Contribution to Development

by José Manuel Gonçalves, Manuel Nunes, Susana Ferreira, António Jordão, José Paixão, Rui Eugénio, António Russo, Henrique Damásio, Isabel Maria Duarte and Kiril Bahcevandziev

Sensors 2022, 22(10), 3632; https://0-doi-org.brum.beds.ac.uk/10.3390/s22103632 - 10 May 2022

Cited by 5 | Viewed by 2083

Abstract

Rice irrigation by continuous flooding is highly water demanding in comparison with most methods applied in the irrigation of other crops, due to a significant deep percolation and surface drainage of paddies. The pollution of water resources and methane emissions are other environmental problems of rice agroecosystems, which require effective agronomic changes to safeguard its sustainable production. To contribute to this solution, an experimental study of alternate wetting and drying flooding (AWD) was carried out in the Center of Portugal in farmer’s paddies, using the methodology of field irrigation evaluation. The AWD results showed that there is a relevant potential to save about 10% of irrigation water with a reduced yield impact, allowing an additional period of about 10 to 29 days of dry soil. The guidelines to promote the on-farm scale AWD automation were outlined, integrating multiple data sources, to get a safe control of soil water and crop productivity. The conclusions point out the advantages of a significant change in the irrigation procedures, the use of water level sensors to assess the right irrigation scheduling to manage the soil deficit and the mild crop stress during the dry periods, and the development of paddy irrigation supplies, to allow a safe and smart AWD. Full article

(This article belongs to the Special Issue Application of Artificial Neural Network and Sensing in Advanced Agriculture)

► Show Figures

Figure 1

14 pages, 2407 KiB

Open AccessArticle

Evolution and Neural Network Prediction of CO₂ Emissions in Weaned Piglet Farms

by Manuel R. Rodriguez, Roberto Besteiro, Juan A. Ortega, Maria D. Fernandez and Tamara Arango

Sensors 2022, 22(8), 2910; https://0-doi-org.brum.beds.ac.uk/10.3390/s22082910 - 11 Apr 2022

Cited by 7 | Viewed by 1844

Abstract

This paper aims to study the evolution of CO₂ concentrations and emissions on a conventional farm with weaned piglets between 6.9 and 17.0 kg live weight based on setpoint temperature, outdoor temperature, and ventilation flow. The experimental trial was conducted during one transition cycle. Generally, the ventilation flow increased with the reduction in setpoint temperature throughout the cycle, which caused a reduction in CO₂ concentration and an increase in emissions. The mean CO₂ concentration was 3.12 g m^–3. Emissions of CO₂ had a mean value of 2.21 mg s⁻¹ per animal, which is equivalent to 0.195 mg s⁻¹ kg⁻¹. A potential function was used to describe the interaction between 10 min values of ventilation flow and CO₂ concentrations, whereas a linear function was used to describe the interaction between 10 min values of ventilation flow and CO₂ emissions, with r values of 0.82 and 0.85, respectively. Using such equations allowed for simple and direct quantification of emissions. Furthermore, two prediction models for CO₂ emissions were developed using two neural networks (for 10 min and 60 min predictions), which reached r values of 0.63 and 0.56. These results are limited mainly by the size of the training period, as well as by the differences between the behavior of the series in the training stage and the testing stage. Full article

(This article belongs to the Special Issue Application of Artificial Neural Network and Sensing in Advanced Agriculture)

► Show Figures

Figure 1

13 pages, 20089 KiB

Open AccessArticle

Soil Water Content Prediction Using Electrical Resistivity Tomography (ERT) in Mediterranean Tree Orchard Soils

by José A. Acosta, María Gabarrón, Marcos Martínez-Segura, Silvia Martínez-Martínez, Ángel Faz, Alejandro Pérez-Pastor, María Dolores Gómez-López and Raúl Zornoza

Sensors 2022, 22(4), 1365; https://0-doi-org.brum.beds.ac.uk/10.3390/s22041365 - 10 Feb 2022

Cited by 11 | Viewed by 2482

Abstract

Water scarcity in arid and semiarid regions poses problems for agricultural systems, awakening special interest in the development of deficit irrigation strategies to improve water conservation. Toward this purpose, farmers and technicians must monitor soil water and soluble nutrient contents in real time using simple, rapid and economical techniques through time and space. Thus, this study aimed to achieve the following: (i) create a model that predicts water and soluble nutrient contents in soil profiles using electrical resistivity tomography (ERT); and (ii) apply the model to different woody crops under different irrigation regimes (full irrigation and regulated deficit irrigation (RDI)) to assess the efficiency of the model. Simple nonlinear regression analysis was carried out on water content and on different ion contents using electrical resistivity data as the dependent variable. A predictive model for soil water content was calibrated and validated with the datasets based on exponential decay of a three-parameter equation. Nonetheless, no accurate model was achieved to predict any soluble nutrient. Electrical resistivity images were replaced by soil water images after application of the predictive model for all studied crops. They showed that under RDI situations, soil profiles became drier at depth while plant roots seemed to uptake more water, contributing to reductions in soil water content by the creation of desiccation bulbs. Therefore, the use of ERT combined with application of the validated predictive model could be a sustainable strategy to monitor soil water evolution in soil profiles under irrigated fields, facilitating land irrigation management. Full article

(This article belongs to the Special Issue Application of Artificial Neural Network and Sensing in Advanced Agriculture)

► Show Figures

Figure 1

16 pages, 3366 KiB

Open AccessArticle

Development of an Algorithm for an Automatic Determination of the Soil Field Capacity Using of a Portable Weighing Lysimeter

by Manuel Soler-Méndez, Dolores Parras-Burgos, Adrián Cisterne-López, Estefanía Mas-Espinosa, Diego S. Intrigliolo and José Miguel Molina-Martínez

Sensors 2021, 21(21), 7203; https://0-doi-org.brum.beds.ac.uk/10.3390/s21217203 - 29 Oct 2021

Cited by 2 | Viewed by 1581

Abstract

The challenge today is to optimize agriculture water consumption and minimize leaching of pollutants in agro-ecosystems in order to ensure a sustainable agriculture. The use of different technologies and the adoption of different irrigation strategies can facilitate efficient fertigation management. In this respect, the determination of soil field capacity point is of utmost importance. The use of a portable weighing lysimeter allows an accurate quantification of crop water consumption and water leaching, as well as the detection of soil field capacity point. In this work, a novel algorithm is developed to obtain the soil field capacity point, in order to give autonomy and objectivity to efficient irrigation management using a portable weighing lysimeter. The development was tested in field grown horticultural crops and proved to be useful for optimizing irrigation management. Full article

(This article belongs to the Special Issue Application of Artificial Neural Network and Sensing in Advanced Agriculture)

► Show Figures

Figure 1

15 pages, 3805 KiB

Open AccessArticle

Optimized Design of Neural Networks for a River Water Level Prediction System

by Miriam López Lineros, Antonio Madueño Luna, Pedro M. Ferreira and Antonio E. Ruano

Sensors 2021, 21(19), 6504; https://0-doi-org.brum.beds.ac.uk/10.3390/s21196504 - 29 Sep 2021

Cited by 9 | Viewed by 1966

Abstract

In this paper, a Multi-Objective Genetic Algorithm (MOGA) framework for the design of Artificial Neural Network (ANN) models is used to design 1-step-ahead prediction models of river water levels. The design procedure is a near-automatic method that, given the data at hand, can partition it into datasets and is able to determine a near-optimal model with the right topology and inputs, offering a good performance on unseen data, i.e., data not used for model design. An example using more than 11 years of water level data (593,178 samples) of the Carrión river collected at Villoldo gauge station shows that the MOGA framework can obtain low-complex models with excellent performance on unseen data, achieving an RMSE of 2.5 × 10⁻³, which compares favorably with results obtained by alternative design. Full article

(This article belongs to the Special Issue Application of Artificial Neural Network and Sensing in Advanced Agriculture)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Application of Artificial Neural Network and Sensing in Advanced Agriculture

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (9 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI