Machine learning in agriculture: from silos to marketplaces

Machine learning for identifying risk of death in patients with severe fever with thrombocytopenia syndrome

Background

Severe fever with thrombocytopenia syndrome (SFTS) has attracted attention due to the rising incidence and high severity and mortality rates. This study aims to construct a machine learning (ML) model to identify SFTS patients at high risk of death early in hospital admission, and to provide early intensive intervention with a view to reducing the risk of death.

Methods

Data of patients hospitalized for SFTS in two hospitals were collected as training and validation sets, respectively, and six ML methods were used to construct the models using the screened variables as features. The performance of the models was comprehensively evaluated and the best model was selected for interpretation and development of an online web calculator for application.

Results

A total of 483 participants were enrolled in the study and 96 (19.88%) patients died due to SFTS. After a comprehensive evaluation, the XGBoost-based model performs best: the AUC scores for the training and validation sets are 0.962 and 0.997.

Conclusion

Using ML can be a good way to identify high risk individuals in SFTS patients. We can use this model to identify patients at high risk of death early in their admission and manage them intensively at an early stage.

Innovative Advances in Plant Genotyping

Over the past decade, advances in plant genotyping have been critical in enabling the identification of genetic diversity, in understanding evolution, and in dissecting important traits in both crops and native plants. The widespread popularity of single-nucleotide polymorphisms (SNPs) has prompted significant improvements to SNP-based genotyping, including SNP arrays, genotyping by sequencing, and whole-genome resequencing. More recent approaches, including genotyping structural variants, utilizing pangenomes to capture species-wide genetic diversity and exploiting machine learning to analyze genotypic data sets, are pushing the boundaries of what plant genotyping can offer. In this chapter, we highlight these innovations and discuss how they will accelerate and advance future genotyping efforts.

Machine Learning System To Monitor Hg2+ and Sulfide Using a Polychromatic Fluorescence-Colorimetric Paper Sensor

An optical monitoring device combining a smartphone with a polychromatic ratiometric fluorescence-colorimetric paper sensor was developed to detect Hg2+ and S2- in water and seafood. This monitoring included the detection of food deterioration and was made possible by processing the sensing data with a machine learning algorithm. The polychromatic fluorescence sensor was composed of blue fluorescent carbon quantum dots (CDs) (BU-CDs) and green and red fluorescent CdZnTe quantum dots (QDs) (named GN-QDs and RD-QDs, respectively). The experimental results and density functional theory (DFT) prove that the incorporation of Zn can improve the stability and quantum yield of CdZnTe QDs. According to the dynamic and static quenching mechanisms, GN-QDs and RD-QDs were quenched by Hg2+ and sulfide, respectively, but BU-CDs were not sensitive to them. The system colors change from green to red to blue as the concentration of the two detectors rises, and the limits of detection (LOD) were 0.002 and 1.488 μM, respectively. Meanwhile, the probe was combined with the hydrogel to construct a visual sensing intelligent test strip, which realized the monitoring of food freshness. In addition, a smartphone device assisted by multiple machine learning methods was used to text Hg2+ and sulfide in real samples. It can be concluded that the fabulous stability, sensitivity, and practicality exhibited by this sensing mechanism give it unlimited potential for assessing the contents of toxic and hazardous substances Hg2+ and sulfide.

Nitrate Classification Based on Optical Absorbance Data Using Machine Learning Algorithms for a Hydroponics System

Nutrient solution plays an essential role in providing macronutrients to hydroponic plants. Determining nitrogen in the form of nitrate is crucial, as either a deficient or excessive supply of nitrate ions may reduce the plant yield or lead to environmental pollution. This work aims to evaluate the performance of feature reduction techniques and conventional machine learning (ML) algorithms in determining nitrate concentration levels. Two features reduction techniques, linear discriminant analysis (LDA) and principal component analysis (PCA), and seven ML algorithms, for example, k-nearest neighbors (KNN), support vector machine, decision trees, naïve bayes, random forest (RF), gradient boosting, and extreme gradient boosting, were evaluated using a high-dimensional spectroscopic dataset containing measured nitrate-nitrite mixed solution absorbance data. Despite the limited and uneven number of samples per class, this study demonstrated that PCA outperformed LDA on the high-dimensional spectroscopic dataset. The classification accuracy of ML algorithms combined with PCA ranged from 92.7% to 99.8%, whereas the classification accuracy of ML algorithms combined with LDA ranged from 80.7% to 87.6%. The PCA with the RF algorithm exhibited the best performance with 99.8% accuracy.

Genetic and molecular factors in determining grain number per panicle of rice

It was suggested that the most effective way to improve rice grain yield is to increase the grain number per panicle (GN) through the breeding practice in recent decades. GN is a representative quantitative trait affected by multiple genetic and environmental factors. Understanding the mechanisms controlling GN has become an important research field in rice biotechnology and breeding. The regulation of rice GN is coordinately controlled by panicle architecture and branch differentiation, and many GN-associated genes showed pleiotropic effect in regulating tillering, grain size, flowering time, and other domestication-related traits. It is also revealed that GN determination is closely related to vascular development and the metabolism of some phytohormones. In this review, we summarize the recent findings in rice GN determination and discuss the genetic and molecular mechanisms of GN regulators.

County-Level Irrigation Water Demand Estimation Using Machine Learning: Case Study of California

Irrigated agriculture is the largest consumer of freshwater globally. Despite the clarity of influential factors and deriving forces, estimation of the volumetric irrigation demand using biophysical models is prohibitively difficult. Data-driven models have proven their ability to predict geophysical and hydrological phenomena with only a handful of influential input variables; however, the lack of reliable input data in most agricultural regions of the world hinders the effectiveness of these approaches. Attempting to estimate the irrigation water demand, we first analyze the correlation of potential influencing variables with irrigation water. We develop machine learning models to predict California’s annual, county-level irrigation water demand based on the statistical analysis findings over an 18-year time span. Input variables are different combinations of deriving meteorological forces, geographical characteristics, cropped area, and crop category. After testing various regression machine learning approaches, the result shows that Gaussian process regression produces the best results. Our findings suggest that irrigated cropped area, air temperature, and vapor pressure deficit are the most significant variables in predicting irrigation water demand. This research also shows that Gaussian process regression can predict irrigation water demand with high accuracy (R2 higher than 0.97 and RMSE as low as 0.06 km3) with different input variable combinations. An accurate estimation of irrigation water use of various crop categories and areas can assist decision-making processes and improve water management strategies. The proposed model can help water policy makers evaluate climatological and agricultural scenarios and hence be used as a decision support tool for agricultural water management at a regional scale.

Advancing designer crops for climate resilience through an integrated genomics approach

Climate change and exponential population growth are exposing an immediate need for developing future crops that are highly resilient and adaptable to changing environments to maintain global food security in the next decade. Rigorous selection from long domestication history has rendered cultivated crops genetically disadvantaged, raising concerns in their ability to adapt to these new challenges and limiting their usefulness in breeding programmes. As a result, future crop improvement efforts must rely on integrating various genomic strategies ranging from high-throughput sequencing to machine learning, in order to exploit germplasm diversity and overcome bottlenecks created by domestication, expansive multi-dimensional phenotypes, arduous breeding processes, complex traits and big data.

Plant Genotype to Phenotype Prediction Using Machine Learning

Genomic prediction tools support crop breeding based on statistical methods, such as the genomic best linear unbiased prediction (GBLUP). However, these tools are not designed to capture non-linear relationships within multi-dimensional datasets, or deal with high dimension datasets such as imagery collected by unmanned aerial vehicles. Machine learning (ML) algorithms have the potential to surpass the prediction accuracy of current tools used for genotype to phenotype prediction, due to their capacity to autonomously extract data features and represent their relationships at multiple levels of abstraction. This review addresses the challenges of applying statistical and machine learning methods for predicting phenotypic traits based on genetic markers, environment data, and imagery for crop breeding. We present the advantages and disadvantages of explainable model structures, discuss the potential of machine learning models for genotype to phenotype prediction in crop breeding, and the challenges, including the scarcity of high-quality datasets, inconsistent metadata annotation and the requirements of ML models.

A Taxonomy of Food Supply Chain Problems from a Computational Intelligence Perspective

In the last few years, the Internet of Things, and other enabling technologies, have been progressively used for digitizing Food Supply Chains (FSC). These and other digitalization-enabling technologies are generating a massive amount of data with enormous potential to manage supply chains more efficiently and sustainably. Nevertheless, the intricate patterns and complexity embedded in large volumes of data present a challenge for systematic human expert analysis. In such a data-driven context, Computational Intelligence (CI) has achieved significant momentum to analyze, mine, and extract the underlying data information, or solve complex optimization problems, striking a balance between productive efficiency and sustainability of food supply systems. Although some recent studies have sorted the CI literature in this field, they are mainly oriented towards a single family of CI methods (a group of methods that share common characteristics) and review their application in specific FSC stages. As such, there is a gap in identifying and classifying FSC problems from a broader perspective, encompassing the various families of CI methods that can be applied in different stages (from production to retailing) and identifying the problems that arise in these stages from a CI perspective. This paper presents a new and comprehensive taxonomy of FSC problems (associated with agriculture, fish farming, and livestock) from a CI approach; that is, it defines FSC problems (from production to retail) and categorizes them based on how they can be modeled from a CI point of view. Furthermore, we review the CI approaches that are more commonly used in each stage of the FSC and in their corresponding categories of problems. We also introduce a set of guidelines to help FSC researchers and practitioners to decide on suitable families of methods when addressing any particular problems they might encounter. Finally, based on the proposed taxonomy, we identify and discuss challenges and research opportunities that the community should explore to enhance the contributions that CI can bring to the digitization of the FSC.

Fast-forward breeding for a food-secure world

Crop production systems need to expand their outputs sustainably to feed a burgeoning human population. Advances in genome sequencing technologies combined with efficient trait mapping procedures accelerate the availability of beneficial alleles for breeding and research. Enhanced interoperability between different omics and phenotyping platforms, leveraged by evolving machine learning tools, will help provide mechanistic explanations for complex plant traits. Targeted and rapid assembly of beneficial alleles using optimized breeding strategies and precise genome editing techniques could deliver ideal crops for the future. Realizing desired productivity gains in the field is imperative for securing an adequate future food supply for 10 billion people.

A Smart and Sustainable Future for Viticulture Is Rooted in Soil: How to Face Cu Toxicity

In recent decades, agriculture has faced the fundamental challenge of needing to increase food production and quality in order to meet the requirements of a growing global population. Similarly, viticulture has also been undergoing change. Several countries are reducing their vineyard areas, and several others are increasing them. In addition, viticulture is moving towards higher altitudes and latitudes due to climate change. Furthermore, global warming is also exacerbating the incidence of fungal diseases in vineyards, forcing farmers to apply agrochemicals to preserve production yields and quality. The repeated application of copper (Cu)-based fungicides in conventional and organic farming has caused a stepwise accumulation of Cu in vineyard soils, posing environmental and toxicological threats. High Cu concentrations in soils can have multiple impacts on agricultural systems. In fact, it can (i) alter the chemical-physical properties of soils, thus compromising their fertility; (ii) induce toxicity phenomena in plants, producing detrimental effects on growth and productivity; and (iii) affect the microbial biodiversity of soils, thereby influencing some microbial-driven soil processes. However, several indirect (e.g., management of rhizosphere processes through intercropping and/or fertilization strategies) and direct (e.g., exploitation of vine resistant genotypes) strategies have been proposed to restrain Cu accumulation in soils. Furthermore, the application of precision and smart viticulture paradigms and their related technologies could allow a timely, localized and balanced distribution of agrochemicals to achieve the required goals. The present review highlights the necessity of applying multidisciplinary approaches to meet the requisites of sustainability demanded of modern viticulture.