Advances in Measurement, Instrument, and Sensing Methods for Sustainable Agriculture

Dear Colleagues,

Sustainable agriculture is agriculture that continuously meets contemporary human needs with regard to the quantity and quality of agricultural products through the management, conservation, and sustainable use of natural resources and through the adaptation of farming systems and technologies without harming the interests of future generations. Additionally, sustainable agriculture maintains and makes rational use of land, water, plant, and animal resources without causing environmental degradation, while being technologically appropriate and feasible, economically viable, and widely accepted by society. Sustainable agriculture is about to shift the paradigm of our current high-input, high-pollution, high-waste agriculture production. To achieve this, modern agriculture needs to treat agricultural information as a factor of agricultural production, and use modern information technology for the visual expression, digital design, and information management of agricultural objects, the environment, and the whole process. Agriculture needs modern technology, especially new measurements, instruments, and sensor methods, more than ever to make it smart. We have seen advances in this field, such as hyperspectral cameras, multispectral cameras, thermal sensors, LiDAR, SAR, etc., mounted on different platforms such as UAVs, mobile vehicles, and towers, and implemented with different analysis methods including graphic methods, computer vision, deep learning, etc. to quantify factors that influence field production. We have seen innovations in measurements and instruments as well, such as handheld devices, ground-penetrating instruments, electronic noses/tongues, biosensors, etc. We have seen the breakthrough in sensing technology that introduced new approaches to agriculture, such as wireless sensor networks, cloud/edge computing, wide-area networks, Internet of Things (IoT), precise satellite navigation/localization, air quality sensors, and soil sensors. To embrace the latest science and technology advances in this field, we are pleased to announce this Special Issue, “Advances in Measurements, Instruments, and sensing methods for Sustainable Agriculture”, which will include all possible topics related to this research field.

For this Special Issue, authors are invited to publish articles focusing on their recent scientific progress and innovations in measurements, instruments, and sensing methods for sustainable agriculture. We welcome novel research, reviews, and opinion papers covering all related topics that promote the application of the latest measurement and sensing techniques, including thermo-acoustic-optical-electromagnetic-based sensors, as well as the latest instruments used in agriculture, such as those used in plant or animal agricultural production, including  for agricultural soils, water, pests, controlled environments, structures, and wastes, in addition to those used on the plants and animals themselves. On-farm, post-harvest operations that considered to be a part of the agricultural process (such as drying, storage, logistics, production assessment, trimming, and separation of plant and animal material) will also be covered.

Dr. Lizhou Xu
Dr. Yanchao Zhang
Dr. Wei Tang
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. Sustainability 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 2400 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.

• agricultural instrument
• remote sensing
• plant phenomics
• biosensors
• electronic nose/tongue
• electrochemical sensors
• optical sensors
• sustainable agriculture

Title: Microalage Astaxanthin Content Detection Based on Hyperspectral Imaging Techniques
Authors: Aiping Gong1, Qibao Wu1,Yongni Shao2, Shanfeng Ling3*
Affiliation: 1. Shenzhen Institute of Information Technology, Shenzhen 518172, China. 2. Shanghai Key Lab of Modern Optical System, University of Shanghai for Science and Technology No. 516, Jungong Road, 200093, Shanghai, China; 3. Shanwei Institute of Technology, Shanwei Guangdong, 516600, China.
Abstract: This study explored the feasibility of using hyperspectral imaging technology to collect algae visible/near-infrared reflectance spectra to establish a quantitative model of astaxanthin for Haematococcus pluvialis. The experiment established a full-wavelength prediction model based on partial least-squares regression (PLS) model. The correlation coefficient (rpre) of the model was 0.972, the prediction root mean square error (RMSEP) was 0.499, and the remaining prediction bias (RPD) reached 4.207. At the same time, we studied and compared the astaxanthin prediction model based on the sensitive wavelengths, and used four feature extraction algorithms to analyze the spectrum. The four algorithms were weighted regression coefficient (BW), principal component load (PCA-loadings), competitive adaptive reweighted sampling (CARS) and successive projection algorithm (SPA). The prediction models based on PLS, multiple linear regression (MLR) and least squares support vector machine (LS-SVM) were established. By comparing the modeling parameters, it was found that the CARS-PLS model established by selecting 32 spectral variables using CARS had the best prediction accuracy. The CARS-PLS model was superior to the full-band model, and the number of variables used was only 6.75% of the number of full-band variables. The experimental results showed that the reflectance spectrum in the range of 425-1023nm can realize the detection of astaxanthin in Haematococcus pluvialis and the prediction formula for astaxanthin content of Haematococcus pluvialis under the optimal model CARS-PLS can be obtained. It was feasible to establish a quantitative model for the astaxanthin content of Haematococcus pluvialis using hyperspectral imaging technology.

Title: Microscopic hyperspectral imaging and deep learning based detection of Mycogone perniciosa chlamydospore in soil
Authors: Xuan Wei, Chuanyuan Xie, Zou Jinping，Zhiqiang Wen，Jiayu Li, Dengfei Jie
Affiliation: College of Mechanical and Electrical Engineering, Fujian Agriculture and Forestry University, Fujian Fuzhou 350002, China
Abstract: The Mycogone perniciosa disease of Agaricus bisporus is characterized by strong contagiousness, insignificant early symptoms and long infestation time and currently there is a lack of a convenient and rapid detection means for early control. This paper is in use of the transmission route of Mycogone perniciosa disease, focus on the M. perniciosa chlamydospore detection in the contaminated soil. The microscopic hyperspectral images of M. perniciosa chlamydospore in contaminated soil were obtained and further be used to establish a detection model. Considering the M. perniciosa chlamydospore is a small target and there is a complex background, we proposed an improved spore detection model based on faster regional convolutional neural network (Faster RCNN) for the detection of M. perniciosa chlamydospore. Combined the residual network Resnet50 and feature pyramid network (FPN) to extract thick spore target features at multiple scales. Meanwhile according to the size of M. perniciosa chlamydospore, in order to improve the performance of the detection model, we optimized the region suggestion network (RPN) suggestion box generation by adding two small sizes of 32 and 64. The first three principal components (with 95% or more information) and RGB image were selected as model inputs, respectively. And the final average precision(AP) of the detection models were 94.68% and 92.35%, respectively. This PC-based model also were compared to other three different models, the VGG16 and Resnet50 based feature extraction networks of Faster RCNN and Darknet53 based feature extraction network of YOLOv3 model, the AP improved with 5.41%, 4.78%, and 6.34%, respectively. The results of this study showed that micro-hyperspectral imaging combined with deep learning methods can detect the chlamydospore in soil exactly, which can provide new methods and ideas for the early prevention and detection of Mycogone perniciosa disease and other fungal diseases of A. bisporus.