Advanced Machine Learning in Point Spectroscopy, RGB- and Hyperspectral-Imaging for Automatic Discriminations of Crops and Weeds: A Review

Farm to fork applications: how vibrational spectroscopy can be used along the whole value chain?

Vibrational spectroscopy is a nondestructive analysis technique that depends on the periodic variations in dipole moments and polarizabilities resulting from the molecular vibrations of molecules/atoms. These methods have important advantages over conventional analytical techniques, including (a) their simplicity in terms of implementation and operation, (b) their adaptability to on-line and on-farm applications, (c) making measurement in a few minutes, and (d) the absence of dangerous solvents throughout sample preparation or measurement. Food safety is a concept that requires the assurance that food is free from any physical, chemical, or biological hazards at all stages, from farm to fork. Continuous monitoring should be provided in order to guarantee the safety of the food. Regarding their advantages, vibrational spectroscopic methods, such as Fourier-transform infrared (FTIR), near-infrared (NIR), and Raman spectroscopy, are considered reliable and rapid techniques to track food safety- and food authenticity-related issues throughout the food chain. Furthermore, coupling spectral data with chemometric approaches also enables the discrimination of samples with different kinds of food safety-related hazards. This review deals with the recent application of vibrational spectroscopic techniques to monitor various hazards related to various foods, including crops, fruits, vegetables, milk, dairy products, meat, seafood, and poultry, throughout harvesting, transportation, processing, distribution, and storage.

Intelligent agriculture: deep learning in UAV-based remote sensing imagery for crop diseases and pests detection

Controlling crop diseases and pests is essential for intelligent agriculture (IA) due to the significant reduction in crop yield and quality caused by these problems. In recent years, the remote sensing (RS) areas has been prevailed over by unmanned aerial vehicle (UAV)-based applications. Herein, by using methods such as keyword co-contribution analysis and author co-occurrence analysis in bibliometrics, we found out the hot-spots of this field. UAV platforms equipped with various types of cameras and other advanced sensors, combined with artificial intelligence (AI) algorithms, especially for deep learning (DL) were reviewed. Acknowledging the critical role of comprehending crop diseases and pests, along with their defining traits, we provided a concise overview as indispensable foundational knowledge. Additionally, some widely used traditional machine learning (ML) algorithms were presented and the performance results were tabulated to form a comparison. Furthermore, we summarized crop diseases and pests monitoring techniques using DL and introduced the application for prediction and classification. Take it a step further, the newest and the most concerned applications of large language model (LLM) and large vision model (LVM) in agriculture were also mentioned herein. At the end of this review, we comprehensively discussed some deficiencies in the existing research and some challenges to be solved, as well as some practical solutions and suggestions in the near future.

Sensing and Perception in Robotic Weeding: Innovations and Limitations for Digital Agriculture

The challenges and drawbacks of manual weeding and herbicide usage, such as inefficiency, high costs, time-consuming tasks, and environmental pollution, have led to a shift in the agricultural industry toward digital agriculture. The utilization of advanced robotic technologies in the process of weeding serves as prominent and symbolic proof of innovations under the umbrella of digital agriculture. Typically, robotic weeding consists of three primary phases: sensing, thinking, and acting. Among these stages, sensing has considerable significance, which has resulted in the development of sophisticated sensing technology. The present study specifically examines a variety of image-based sensing systems, such as RGB, NIR, spectral, and thermal cameras. Furthermore, it discusses non-imaging systems, including lasers, seed mapping, LIDAR, ToF, and ultrasonic systems. Regarding the benefits, we can highlight the reduced expenses and zero water and soil pollution. As for the obstacles, we can point out the significant initial investment, limited precision, unfavorable environmental circumstances, as well as the scarcity of professionals and subject knowledge. This study intends to address the advantages and challenges associated with each of these sensing technologies. Moreover, the technical remarks and solutions explored in this investigation provide a straightforward framework for future studies by both scholars and administrators in the context of robotic weeding.

Artificial Intelligence Techniques in Grapevine Research: A Comparative Study with an Extensive Review of Datasets, Diseases, and Techniques Evaluation

In the last few years, the agricultural field has undergone a digital transformation, incorporating artificial intelligence systems to make good employment of the growing volume of data from various sources and derive value from it. Within artificial intelligence, Machine Learning is a powerful tool for confronting the numerous challenges of developing knowledge-based farming systems. This study aims to comprehensively review the current scientific literature from 2017 to 2023, emphasizing Machine Learning in agriculture, especially viticulture, to detect and predict grape infections. Most of these studies (88%) were conducted within the last five years. A variety of Machine Learning algorithms were used, with those belonging to the Neural Networks (especially Convolutional Neural Networks) standing out as having the best results most of the time. Out of the list of diseases, the ones most researched were Grapevine Yellow, Flavescence Dorée, Esca, Downy mildew, Leafroll, Pierce's, and Root Rot. Also, some other fields were studied, namely Water Management, plant deficiencies, and classification. Because of the difficulty of the topic, we collected all datasets that were available about grapevines, and we described each dataset with the type of data (e.g., statistical, images, type of images), along with the number of images where they were mentioned. This work provides a unique source of information for a general audience comprising AI researchers, agricultural scientists, wine grape growers, and policymakers. Among others, its outcomes could be effective in curbing diseases in viticulture, which in turn will drive sustainable gains and boost success. Additionally, it could help build resilience in related farming industries such as winemaking.

De novo domestication: what about the weeds?

Most high-yielding crops are susceptible to abiotic and biotic stresses, making them particularly vulnerable to the potential effects of climate change. A possible alternative is to accelerate the domestication of wild plants that are already tolerant to harsh conditions and to increase their yields by methods such as gene editing. We foresee that crops' wild progenitors could potentially compete with the resulting de novo domesticated plants, reducing yields. To improve the recognition of weeds, we propose using gene editing techniques to introduce traits into de novo domesticated crops that will allow for visual recognition of the crops by weeding robots that have been trained by machine learning.

Innovative spectral characterisation of beached pelagic sargassum towards remote estimation of biochemical and phenotypic properties

In recent years, pelagic sargassum (S. fluitans and S. natans - henceforth sargassum) macroalgal blooms have become more frequent and larger with higher biomass in the Tropical Atlantic region. They have environmental and socio-economic impacts, particularly on coastal ecosystems, tourism, fisheries and aquaculture industries, and on public health. Despite these challenges, sargassum biomass has the potential to offer commercial opportunities in the blue economy, although, it is reliant on key chemical and physical characteristics of the sargassum for specific use. In this study, we aim to utilise remotely sensed spectral profiles to determine species/morphotypes at different decomposition stages and their biochemical composition to support monitoring and valorisation of sargassum. For this, we undertook dedicated field campaigns in Barbados and Ghana to collect, for the first time, in situ spectral measurements between 350 and 2500 nm using a Spectra Vista Corp (SVC) HR-1024i field spectrometer of pelagic sargassum stranded biomass. The spectral measurements were complemented by uncrewed aerial system surveys using a DJI Phantom 4 drone and a DJI P4 multispectral instrument. Using the ground and airborne datasets this research developed an operational framework for remote detection of beached sargassum; and created spectral profiles of species/morphotypes and decomposition maps to infer biochemical composition. We were able to identify some key spectral regions, including a consistent absorption feature (920-1080 nm) found in all of the sargassum morphotype spectral profiles; we also observed distinction between fresh and recently beached sargassum particularly around 900-1000 nm. This work can support pelagic sargassum management and contribute to effective utilisation of the sargassum biomass to ultimately alleviate some of the socio-economic impacts associated with this emerging environmental challenge.

Omics-driven exploration and mining of key functional genes for the improvement of food and fiber crops

The deployment of omics technologies has obtained an incredible boost over the past few decades with the advances in next-generation sequencing (NGS) technologies, innovative bioinformatics tools, and the deluge of available biological information. The major omics technologies in the limelight are genomics, transcriptomics, proteomics, metabolomics, and phenomics. These biotechnological advances have modernized crop breeding and opened new horizons for developing crop varieties with improved traits. The genomes of several crop species are sequenced, and a huge number of genes associated with crucial economic traits have been identified. These identified genes not only provide insights into the understanding of regulatory mechanisms of crop traits but also decipher practical grounds to assist in the molecular breeding of crops. This review discusses the potential of omics technologies for the acquisition of biological information and mining of the genes associated with important agronomic traits in important food and fiber crops, such as wheat, rice, maize, potato, tomato, cassava, and cotton. Different functional genomics approaches for the validation of these important genes are also highlighted. Furthermore, a list of genes discovered by employing omics approaches is being represented as potential targets for genetic modifications by the latest genome engineering methods for the development of climate-resilient crops that would in turn provide great impetus to secure global food security.

A Prototype Method for the Detection and Recognition of Pigments in the Environment Based on Optical Property Simulation

The possibility of pigment detection and recognition in different environments such as solvents or proteins is a challenging, and at the same time demanding, task. It may be needed in very different situations: from the nondestructive in situ identification of pigments in paintings to the early detection of fungal infection in major agro-industrial crops and products. So, we propose a prototype method, the key feature of which is a procedure analyzing the lineshape of a spectrum. The shape of the absorption spectrum corresponding to this transition strongly depends on the immediate environment of a pigment and can serve as a marker to detect the presence of a particular pigment molecule in a sample. Considering carotenoids as an object of study, we demonstrate that the combined operation of the differential evolution algorithm and semiclassical quantum modeling of the optical response based on a generalized spectral density (the number of vibronic modes is arbitrary) allows us to distinguish quantum models of the pigment for different solvents. Moreover, it is determined that to predict the optical properties of monomeric pigments in protein, it is necessary to create a database containing, for each pigment, in addition to the absorption spectra measured in a predefined set of solvents, the parameters of the quantum model found using differential evolution.

Data Augmentation Techniques for Machine Learning Applied to Optical Spectroscopy Datasets in Agrifood Applications: A Comprehensive Review

Machine learning (ML) and deep learning (DL) have achieved great success in different tasks. These include computer vision, image segmentation, natural language processing, predicting classification, evaluating time series, and predicting values based on a series of variables. As artificial intelligence progresses, new techniques are being applied to areas like optical spectroscopy and its uses in specific fields, such as the agrifood industry. The performance of ML and DL techniques generally improves with the amount of data available. However, it is not always possible to obtain all the necessary data for creating a robust dataset. In the particular case of agrifood applications, dataset collection is generally constrained to specific periods. Weather conditions can also reduce the possibility to cover the entire range of classifications with the consequent generation of imbalanced datasets. To address this issue, data augmentation (DA) techniques are employed to expand the dataset by adding slightly modified copies of existing data. This leads to a dataset that includes values from laboratory tests, as well as a collection of synthetic data based on the real data. This review work will present the application of DA techniques to optical spectroscopy datasets obtained from real agrifood industry applications. The reviewed methods will describe the use of simple DA techniques, such as duplicating samples with slight changes, as well as the utilization of more complex algorithms based on deep learning generative adversarial networks (GANs), and semi-supervised generative adversarial networks (SGANs).

Investigation on the use of ensemble learning and big data in crop identification

The agriculture sector in Egypt faces several problems, such as climate change, water storage, and yield variability. The comprehensive capabilities of Big Data (BD) can help in tackling the uncertainty of food supply occurs due to several factors such as soil erosion, water pollution, climate change, socio-cultural growth, governmental regulations, and market fluctuations. Crop identification and monitoring plays a vital role in modern agriculture. Although several machine learning models have been utilized in identifying crops, the performance of ensemble learning has not been investigated extensively. The massive volume of satellite imageries has been established as a big data problem forcing to deploy the proposed solution using big data technologies to manage, store, analyze, and visualize satellite data. In this paper, we have developed a weighted voting mechanism for improving crop classification performance in a large scale, based on ensemble learning and big data schema. Built upon Apache Spark, the popular DB Framework, the proposed approach was tested on El Salheya, Ismaili governate. The proposed ensemble approach boosted accuracy by 6.5%, 1.9%, 4.4%, 4.9%, 4.7% in precision, recall, F-score, Overall Accuracy (OA), and Matthews correlation coefficient (MCC) metrics respectively. Our findings confirm the generalization of the proposed crop identification approach at a large-scale setting.

Soybean cyst nematode detection and management: a review

Soybeans play a key role in global food security. U.S. soybean yields, which comprise [Formula: see text] of the total soybeans planted in the world, continue to experience unprecedented grain loss due to the soybean cyst nematode (SCN) plant pathogen. SCN remains one of the primary disruptive pests despite the existence of advanced management techniques such as crop rotation and SCN-resistant varieties. SCN detection is a key step in managing this disease; however, early detection is challenging because soybeans do not show any above ground symptoms unless they  are significantly damaged. Direct soil sampling remains the most common method for SCN detection, however, this method has several problems. For example, the threshold damage methods-adopted by most of the laboratories to make recommendations-is not reliable as it does not consider soil pH, N, P, and K values and relies solely on the egg count instead of assessment of the root infection. To overcome the challenges of manual soil sampling methods, deep learning and hyperspectral imaging are important current topics in precision agriculture for plant disease detection and have been proposed as cost-effective and efficient detection methods that can work at scale. We have reviewed more than 150 research papers focusing on soybean cyst nematodes with an emphasis on deep learning techniques for detection and management. First: we describe soybean vegetation and reproduction stages, SCN life cycles, and factors influencing this disease. Second: we highlight the impact of SCN on soybean yield loss and the challenges associated with its detection. Third: we describe direct sampling methods in which the soil samples are procured and analyzed to evaluate SCN egg counts. Fourth: we highlight the advantages and limitations of these direct methods, then review computer vision- and remote sensing-based detection methods: data collection using ground, aerial, and satellite approaches followed by a review of machine learning methods for image analysis-based soybean cyst nematode detection. We highlight the evaluation approaches and the advantages of overall detection workflow in high-performance and big data environments. Lastly, we discuss various management approaches, such as crop rotation, fertilization, SCN resistant varieties such as PI 88788, and SCN's increasing resistance to these strategies. We review machine learning approaches for soybean crop yield forecasting as well as the influence of pesticides, herbicides, and fertilizers on SCN infestation reduction. We provide recommendations for soybean research using deep learning and hyperspectral imaging to accommodate the lack of the ground truth data and training and testing methodologies, such as data augmentation and transfer learning, to achieve a high level of detection accuracy while keeping costs as low as possible.

Two-Stage Convolutional Neural Networks for Diagnosing the Severity of Alternaria Leaf Blotch Disease of the Apple Tree

In many parts of the world, apple trees suffer from severe foliar damage each year due to infection of Alternaria blotch (Alternaria alternata f. sp. Mali), resulting in serious economic losses to growers. Traditional methods for disease detection and severity classification mostly rely on manual labor, which is slow, labor-intensive and highly subjective. There is an urgent need to develop an effective protocol to rapidly and accurately evaluate disease severity. In this study, DeeplabV3+, PSPNet and UNet were used to assess the severity of apple Alternaria leaf blotch. For identifications of leaves and disease areas, the dataset with a total of 5382 samples was randomly split into 74% (4004 samples) for model training, 9% (494 samples) for validation, 8% (444 samples) for testing and 8% (440 samples) for overall testing. Apple leaves were first segmented from complex backgrounds using the deep-learning algorithms with different backbones. Then, the recognition of disease areas was performed on the segmented leaves. The results showed that the PSPNet model with MobileNetV2 backbone exhibited the highest performance in leaf segmentation, with precision, recall and MIoU values of 99.15%, 99.26% and 98.42%, respectively. The UNet model with VGG backbone performed the best in disease-area prediction, with a precision of 95.84%, a recall of 95.54% and a MIoU value of 92.05%. The ratio of disease area to leaf area was calculated to assess the disease severity. The results showed that the average accuracy for severity classification was 96.41%. Moreover, both the correlation coefficient and the consistency correlation coefficient were 0.992, indicating a high agreement between the reference values and the value that the research predicted. This study proves the feasibility of rapid estimation of the severity of apple Alternaria leaf blotch, which will provide technical support for precise application of pesticides.

Assessment of Invasive and Weed Species by Hyperspectral Imagery in Agrocenoses Ecosystem

The present study aimed to investigate the possibility of using hyperspectral imaging data to identify the invasive and weed species in agrocenoses ecosystem. The most common weeds in grain agrocenoses, i.e., Ambrosia artemisiifolia L., Euphorbia seguieriana Neck., Atriplex tatarica L., Glycyrrhiza glabra L., Setaria pumila (Poir.) Roem. and Schult, served as objects. The population of weeds, especially Ambrosia artemisiifolia is invasive for the selected region of study. Therefore, the shooting of objects was carried out with a hyperspectral camera, Cubert UHD185, and the values of 100 spectral channels were obtained from hyperspectral images. The values of 80 vegetation indices (VIs) were calculated. The material was processed using mathematical statistics (analysis of variance, t-test) and search methods of data analysis (principal component analysis, decision tree, and random forest). Using statistical methods, the simultaneous use of several VIs differentiated between species more deliberately and precisely. The combination of VIs Derivative index (D1), Chlorophyll content index (Datt3), and Pigment specific normalized difference (PSND) can be used for weeds identification. Using the decision tree method, VIs established a good division of weeds into groups; (1) perennial rhizomatous weeds (Euphorbia seguieriana, and Glycyrrhiza glabra), and (2) annual weeds (A. artemisiifolia, A. tatarica, and S. pumila); These Vis are Chlorophyll index (CI), D1, and Datt3. Using the random forest method, the VIs that have the greatest impact on Mean Decrease Accuracy and Mean Decrease Gini are D1, Datt3, PSND, and Double Peak Index (DPI). The use of spectral channel values for the identification of plant species using the principal component analysis, decision tree, and random forest methods showed worse results than when using VIs. A great similarity of the results was obtained with the help of statistical and search methods of data analysis.

Surveying soil-borne disease development on wild rocket salad crop by proximal sensing based on high-resolution hyperspectral features

Wild rocket (Diplotaxis tenuifolia, Brassicaceae) is a baby-leaf vegetable crop of high economic interest, used in ready-to-eat minimally processed salads, with an appreciated taste and nutraceutical features. Disease management is key to achieving the sustainability of the entire production chain in intensive systems, where synthetic fungicides are limited or not permitted. In this context, soil-borne pathologies, much feared by growers, are becoming a real emergency. Digital screening of green beds can be implemented in order to optimize the use of sustainable means. The current study used a high-resolution hyperspectral array (spectroscopy at 350-2500 nm) to attempt to follow the progression of symptoms of Rhizoctonia, Sclerotinia, and Sclerotium disease across four different severity levels. A Random Forest machine learning model reduced dimensions of the training big dataset allowing to compute de novo vegetation indices specifically informative about canopy decay caused by all basal pathogenic attacks. Their transferability was also tested on the canopy dataset, which was useful for assessing the health status of wild rocket plants. Indeed, the progression of symptoms associated with soil-borne pathogens is closely related to the reduction of leaf absorbance of the canopy in certain ranges of visible and shortwave infrared spectral regions sensitive to reduction of chlorophyll and other pigments as well as to modifications of water content and turgor.

Recognition and Localization of Target Images for Robot Vision Navigation Control

This paper focuses on a visual navigation control system for mobile robots, recognizing target images and intelligent algorithms for the navigation system’s path tracking and localization techniques. This paper examines the recognition and localization of target images based on the visual navigation control of mobile robots. It proposes an efficient marking line method for recognizing and localization target images. Meanwhile, a fuzzy control method with smooth filtering and high efficiency is designed to improve the stability of robot operation, and the feasibility is verified in different scenarios. The corresponding image acquisition system is developed according to the characteristics of the experimental environment, and the acquired images are preprocessed to obtain corrected grayscale images. Then, target image recognition and linear fitting are performed to obtain target image positioning. The system calculates the angle and distance of the mobile robot, offsetting the target image in real time, adjusting the output signal, and controlling the mobile robot to realize path tracking. The comparison of sensor data and path tracking algorithm results during the experiment shows that the path tracking algorithm achieves good results with an angular deviation of ±1.5°. The application of RANSAC algorithm and improved Hough algorithm was analyzed in visual navigation control, and the two navigation line detection algorithms based on the image characteristics of the target image were improved in the optical detection area of the navigation line for the shortcomings of the two algorithms in visual navigation control, and the algorithms before and after the improvement were compared.

The Application of Hyperspectral Remote Sensing Imagery (HRSI) for Weed Detection Analysis in Rice Fields: A Review

Weeds are found on every cropland across the world. Weeds compete for light, water, and nutrients with attractive plants, introduce illnesses or viruses, and attract harmful insects and pests, resulting in yield loss. New weed detection technologies have been developed in recent years to increase weed detection speed and accuracy, resolving the contradiction between the goals of enhancing soil health and achieving sufficient weed control for profitable farming. In recent years, a variety of platforms, such as satellites, airplanes, unmanned aerial vehicles (UAVs), and close-range platforms, have become more commonly available for gathering hyperspectral images with varying spatial, temporal, and spectral resolutions. Plants must be divided into crops and weeds based on their species for successful weed detection. Therefore, hyperspectral image categorization also has become popular since the development of hyperspectral image technology. Unmanned aerial vehicle (UAV) hyperspectral imaging techniques have recently emerged as a valuable tool in agricultural remote sensing, with tremendous promise for weed detection and species separation. Hence, this paper will review the weeds problem in rice fields in Malaysia and focus on the application of hyperspectral remote sensing imagery (HRSI) for weed detection with algorithms and modelling employed for weeds discrimination analysis.

Development of novel robotic platforms for mechanical stress induction, and their effects on plant morphology, elements, and metabolism

This research evaluates the effect on herbal crops of mechanical stress induced by two specially developed robotic platforms. The changes in plant morphology, metabolite profiles, and element content are evaluated in a series of three empirical experiments, conducted in greenhouse and CNC growing bed conditions, for the case of basil plant growth. Results show significant changes in morphological features, including shortening of overall stem length by up to 40% and inter-node distances by up to 80%, for plants treated with a robotic mechanical stress-induction protocol, compared to control groups. Treated plants showed a significant increase in element absorption, by 20–250% compared to controls, and changes in the metabolite profiles suggested an improvement in plants’ nutritional profiles. These results suggest that repetitive, robotic, mechanical stimuli could be potentially beneficial for plants’ nutritional and taste properties, and could be performed with no human intervention (and therefore labor cost). The changes in morphological aspects of the plant could potentially replace practices involving chemical treatment of the plants, leading to more sustainable crop production.

Mobile Application Development for Spectral Signature of Weed Species in Rice Farming

Weed infestation happens when there is intense competition between rice and weeds for light, nutrients and water. These conditions need to be monitored and controlled to lower the growth of weeds as they affected crops production. The characteristics of weeds and rice are challenging to differentiate macroscopically. However, information can be acquired using a spectral signature graph. Hence, this study emphasises using the spectral signature of weed species and rice in a rice field. The study aims to generate a spectral signature graph of weeds in rice fields and develop a mobile application for the spectral signature of weeds. Six weeds were identified in Ladang Merdeka using Fieldspec HandHeld 2 Spectroradiometer. All the spectral signatures were stored in a spectral database using Apps Master Builder, viewed using smartphones. The results from the spectral signature graph show that the jungle rice (Echinochloa spp.) has the highest near-infrared (NIR) reflectance. In contrast, the saromacca grass (Ischaemum rugosum) shows the lowest NIR reflectance. Then, the first derivative (FD) analysis was run to visualise the separation of each species, and the 710 nm to 750 nm region shows the highest separation. It shows that the weed species can be identified using spectral signature by FD analysis with accurate separation. The mobile application was developed to provide information about the weeds and control methods to the users. Users can access information regarding weeds and take action based on the recommendations of the mobile application.

Imaging Spectroscopy and Machine Learning for Intelligent Determination of Potato and Sweet Potato Quality

Imaging spectroscopy has emerged as a reliable analytical method for effectively characterizing and quantifying quality attributes of agricultural products. By providing spectral information relevant to food quality properties, imaging spectroscopy has been demonstrated to be a potential method for rapid and non-destructive classification, authentication, and prediction of quality parameters of various categories of tubers, including potato and sweet potato. The imaging technique has demonstrated great capacities for gaining rapid information about tuber physical properties (such as texture, water binding capacity, and specific gravity), chemical components (such as protein, starch, and total anthocyanin), varietal authentication, and defect aspects. This paper emphasizes how recent developments in spectral imaging with machine learning have enhanced overall capabilities to evaluate tubers. The machine learning algorithms coupled with feature variable identification approaches have obtained acceptable results. This review briefly introduces imaging spectroscopy and machine learning, then provides examples and discussions of these techniques in tuber quality determinations, and presents the challenges and future prospects of the technology. This review will be of great significance to the study of tubers using spectral imaging technology.

Machine Learning in Agriculture: A Comprehensive Updated Review

The digital transformation of agriculture has evolved various aspects of management into artificial intelligent systems for the sake of making value from the ever-increasing data originated from numerous sources. A subset of artificial intelligence, namely machine learning, has a considerable potential to handle numerous challenges in the establishment of knowledge-based farming systems. The present study aims at shedding light on machine learning in agriculture by thoroughly reviewing the recent scholarly literature based on keywords' combinations of "machine learning" along with "crop management", "water management", "soil management", and "livestock management", and in accordance with PRISMA guidelines. Only journal papers were considered eligible that were published within 2018-2020. The results indicated that this topic pertains to different disciplines that favour convergence research at the international level. Furthermore, crop management was observed to be at the centre of attention. A plethora of machine learning algorithms were used, with those belonging to Artificial Neural Networks being more efficient. In addition, maize and wheat as well as cattle and sheep were the most investigated crops and animals, respectively. Finally, a variety of sensors, attached on satellites and unmanned ground and aerial vehicles, have been utilized as a means of getting reliable input data for the data analyses. It is anticipated that this study will constitute a beneficial guide to all stakeholders towards enhancing awareness of the potential advantages of using machine learning in agriculture and contributing to a more systematic research on this topic.

Review of Weed Detection Methods Based on Computer Vision

Weeds are one of the most important factors affecting agricultural production. The waste and pollution of farmland ecological environment caused by full-coverage chemical herbicide spraying are becoming increasingly evident. With the continuous improvement in the agricultural production level, accurately distinguishing crops from weeds and achieving precise spraying only for weeds are important. However, precise spraying depends on accurately identifying and locating weeds and crops. In recent years, some scholars have used various computer vision methods to achieve this purpose. This review elaborates the two aspects of using traditional image-processing methods and deep learning-based methods to solve weed detection problems. It provides an overview of various methods for weed detection in recent years, analyzes the advantages and disadvantages of existing methods, and introduces several related plant leaves, weed datasets, and weeding machinery. Lastly, the problems and difficulties of the existing weed detection methods are analyzed, and the development trend of future research is prospected.

Machine Learning-Based Prediction of Selected Parameters of Commercial Biomass Pellets Using Line Scan Near Infrared-Hyperspectral Image

Biomass pellets are required as a source of energy because of their abundant and high energy. The rapid measurement of pellets is used to control the biomass quality during the production process. The objective of this work was to use near infrared (NIR) hyperspectral images for predicting the properties, i.e., fuel ratio (FR), volatile matter (VM), fixed carbon (FC), and ash content (A), of commercial biomass pellets. Models were developed using either full spectra or different spatial wavelengths, i.e., interval successive projections algorithm (iSPA) and interval genetic algorithm (iGA), wavelengths and different spectral preprocessing techniques. Their performances were then compared. The optimal model for predicting FR could be created with second derivative (D2) spectra with iSPA-100 wavelengths, while VM, FC, and A could be predicted using standard normal variate (SNV) spectra with iSPA-100 wavelengths. The models for predicting FR, VM, FC, and A provided R2 values of 0.75, 0.81, 0.82, and 0.87, respectively. Finally, the prediction of the biomass pellets’ properties under color distribution mapping was able to track pellet quality to control and monitor quality during the operation of the thermal conversion process and can be intuitively used for applications with screening.

Weed and Corn Seedling Detection in Field Based on Multi Feature Fusion and Support Vector Machine

Detection of weeds and crops is the key step for precision spraying using the spraying herbicide robot and precise fertilization for the agriculture machine in the field. On the basis of k-mean clustering image segmentation using color information and connected region analysis, a method combining multi feature fusion and support vector machine (SVM) was proposed to identify and detect the position of corn seedlings and weeds, to reduce the harm of weeds on corn growth, and to achieve accurate fertilization, thereby realizing precise weeding or fertilizing. First, the image dataset for weed and corn seedling classification in the corn seedling stage was established. Second, many different features of corn seedlings and weeds were extracted, and dimensionality was reduced by principal component analysis, including the histogram of oriented gradient feature, rotation invariant local binary pattern (LBP) feature, Hu invariant moment feature, Gabor feature, gray level co-occurrence matrix, and gray level-gradient co-occurrence matrix. Then, the classifier training based on SVM was conducted to obtain the recognition model for corn seedlings and weeds. The comprehensive recognition performance of single feature or different fusion strategies for six features is compared and analyzed, and the optimal feature fusion strategy is obtained. Finally, by utilizing the actual corn seedling field images, the proposed weed and corn seedling detection method effect was tested. LAB color space and K-means clustering were used to achieve image segmentation. Connected component analysis was adopted to remove small objects. The previously trained recognition model was utilized to identify and label each connected region to identify and detect weeds and corn seedlings. The experimental results showed that the fusion feature combination of rotation invariant LBP feature and gray level-gradient co-occurrence matrix based on SVM classifier obtained the highest classification accuracy and accurately detected all kinds of weeds and corn seedlings. It provided information on weed and crop positions to the spraying herbicide robot for accurate spraying or to the precise fertilization machine for accurate fertilizing.

Automatic Evaluation of Wheat Resistance to Fusarium Head Blight Using Dual Mask-RCNN Deep Learning Frameworks in Computer Vision

In many regions of the world, wheat is vulnerable to severe yield and quality losses from the fungus disease of Fusarium head blight (FHB). The development of resistant cultivars is one means of ameliorating the devastating effects of this disease, but the breeding process requires the evaluation of hundreds of lines each year for reaction to the disease. These field evaluations are laborious, expensive, time-consuming, and are prone to rater error. A phenotyping cart that can quickly capture images of the spikes of wheat lines and their level of FHB infection would greatly benefit wheat breeding programs. In this study, mask region convolutional neural network (Mask-RCNN) allowed for reliable identification of the symptom location and the disease severity of wheat spikes. Within a wheat line planted in the field, color images of individual wheat spikes and their corresponding diseased areas were labeled and segmented into sub-images. Images with annotated spikes and sub-images of individual spikes with labeled diseased areas were used as ground truth data to train Mask-RCNN models for automatic image segmentation of wheat spikes and FHB diseased areas, respectively. The feature pyramid network (FPN) based on ResNet-101 network was used as the backbone of Mask-RCNN for constructing the feature pyramid and extracting features. After generating mask images of wheat spikes from full-size images, Mask-RCNN was performed to predict diseased areas on each individual spike. This protocol enabled the rapid recognition of wheat spikes and diseased areas with the detection rates of 77.76% and 98.81%, respectively. The prediction accuracy of 77.19% was achieved by calculating the ratio of the wheat FHB severity value of prediction over ground truth. This study demonstrates the feasibility of rapidly determining levels of FHB in wheat spikes, which will greatly facilitate the breeding of resistant cultivars.

Hyperspectral imaging and improved feature variable selection for automated determination of deoxynivalenol in various genetic lines of barley kernels for resistance screening

Fusarium head blight (FHB), a fungus disease of small grain cereal crops, results in reduced yields and diminished value of harvested grain due to the presence of deoxynivalenol (DON), a mycotoxin produced by the causal pathogen Fusarium graminearum. DON and other tricothecene mycotoxins pose serious health risks to both humans and livestock, especially swine. Due to these health concerns, barley used for malting, food or feed is routinely assayed for DON levels. Various methods are available for assaying DON levels in grain samples including enzyme-linked immunosorbent assay (ELISA) and gas chromatography-mass spectrometry (GC-MS). ELISA and GC-MS are very accurate; however, assaying grain samples by these techniques are laborious, expensive and destructive. In this study, we explored the feasibility of using hyperspectral imaging (382-1030 nm) to develop a rapid and non-destructive protocol for assaying DON in barley kernels. Samples of 888 and 116 from various genetic lines were selected for calibration and prediction. Full-wavelength locally weighted partial least squares regression (LWPLSR) achieved high accuracy with the coefficient of determination in prediction (R²_P) of 0.728 and root mean square error of prediction (RMSEP) of 3.802. Competitive adaptive reweighted sampling (CARS) was used to choose potential feature wavelengths, and these selected variables were further optimized using the iterative selection of successive projections algorithm (ISSPA). The CARS-ISSPA-LWPLSR model developed using 7 feature variables yielded R²_P of 0.680 and RMSEP of 4.213 in DON content prediction. Based on the 7 wavelengths selected by CARS-ISSPA, partial least square discriminant analysis (PLSDA) discriminated barley kernels having lower DON (less than1.25 mg/kg) levels from those with higher levels (including 1.25-3 mg/kg, 3-5 mg/kg, and 5-10 mg/kg), with Matthews correlation coefficient in cross-validation (M-R_CV) of as high as 0.931. The results demonstrate that hyperspectral imaging have potential for accelerating non-destructive DON assays of barley samples.