Optimizing the Energy Efficiency of Unreliable Memories for Quantized Kalman Filtering.

This paper presents a quantized Kalman filter implemented using unreliable memories. We consider that both the quantization and the unreliable memories introduce errors in the computations, and we develop an error propagation model that takes into account these two sources of errors. In addition to providing updated Kalman filter equations, the proposed error model accurately predicts the covariance of the estimation error and gives a relation between the performance of the filter and its energy consumption, depending on the noise level in the memories. Then, since memories are responsible for a large part of the energy consumption of embedded systems, optimization methods are introduced to minimize the memory energy consumption under the desired estimation performance of the filter. The first method computes the optimal energy levels allocated to each memory bank individually, and the second one optimizes the energy allocation per groups of memory banks. Simulations show a close match between the theoretical analysis and experimental results. Furthermore, they demonstrate an important reduction in energy consumption of more than 50%.

Smartphone Application-Enabled Apple Fruit Surface Temperature Monitoring Tool for In-Field and Real-Time Sunburn Susceptibility Prediction.

Heat stress and resulting sunburn is a major abiotic stress in perineal specialty crops. For example, such stress to the maturing fruits on apple tree canopies can cause several physiological disorders that result in considerable crop losses and reduced marketability of the produce. Thus, there is a critical technological need to effectively monitor the abiotic stress under field conditions for timely actuation of remedial measures. Fruit surface temperature (FST) is one of the stress indicators that can reliably be used to predict apple fruit sunburn susceptibility. This study was therefore focused on development and in-field testing of a mobile FST monitoring tool that can be used for real-time crop stress monitoring. The tool integrates a smartphone connected thermal-Red-Green-Blue (RGB) imaging sensor and a custom developed application ('AppSense 1.0') for apple fruit sunburn prediction. This tool is configured to acquire and analyze imagery data onboard the smartphone to estimate FST. The tool also utilizes geolocation-specific weather data to estimate weather-based FST using an energy balance modeling approach. The 'AppSense 1.0' application, developed to work in the Android operating system, allows visual display, annotation and real-time sharing of the imagery, weather data and pertinent FST estimates. The developed tool was evaluated in orchard conditions during the 2019 crop production season on the Gala, Fuji, Red delicious and Honeycrisp apple cultivars. Overall, results showed no significant difference (t110 = 0.51, p = 0.6) between the mobile FST monitoring tool outputs, and ground truth FST data collected using a thermal probe which had accuracy of ±0.4 °C. Upon further refinements, such tool could aid growers in real-time apple fruit sunburn susceptibility prediction and assist in more effective actuation of apple fruit sunburn preventative measures. This tool also has the potential to be customized for in-field monitoring of the heat stressors in some of the sun-exposed perennial and annual specialty crops at produce maturation.

Feasibility of Volatile Biomarker-Based Detection of Pythium Leak in Postharvest Stored Potato Tubers Using Field Asymmetric Ion Mobility Spectrometry.

The study evaluates the suitability of a field asymmetric ion mobility spectrometry (FAIMS) system for early detection of the Pythium leak disease in potato tubers simulating bulk storage conditions. Tubers of Ranger Russet (RR) and Russet Burbank (RB) cultivars were inoculated with Pythium ultimum, the causal agent of Pythium leak (with negative control samples as well) and placed in glass jars. The headspace in sampling jars was scanned using the FAIMS system at regular intervals (in days up to 14 and 31 days for the tubers stored at 25 °C and 4 °C, respectively) to acquire ion mobility current profiles representing the volatile organic compounds (VOCs). Principal component analysis plots revealed that VOCs ion peak profiles specific to Pythium ultimum were detected for the cultivars as early as one day after inoculation (DAI) at room temperature storage condition, while delayed detection was observed for tubers stored at 4 °C (RR: 5th DAI and RB: 10th DAI), possibly due to a slower disease progression at a lower temperature. There was also some overlap between control and inoculated samples at a lower temperature, which could be because of the limited volatile release. Additionally, data suggested that the RB cultivar might be less susceptible to Pythium ultimum under reduced temperature storage conditions. Disease symptom-specific critical compensation voltage (CV) and dispersion field (DF) from FAIMS responses were in the ranges of -0.58 to -2.97 V and 30-84% for the tubers stored at room temperature, and -0.31 to -2.97 V and 28-90% for reduced temperature, respectively. The ion current intensities at -1.31 V CV and 74% DF showed distinctive temporal progression associated with healthy control and infected tuber samples.

Hyperspectral Imaging and Spectrometry-Derived Spectral Features for Bitter Pit Detection in Storage Apples.

Bitter pit is one of the most important disorders in apples. Some of the fresh market apple varieties are susceptible to bitter pit disorder. In this study, visible⁻near-infrared spectrometry-based reflectance spectral data (350⁻2500 nm) were acquired from 2014, 2015 and 2016 harvest produce after 63 days of storage at 5 °C. Selected spectral features from 2014 season were used to classify the healthy and bitter pit samples from three years. In addition, these spectral features were also validated using hyperspectral imagery data collected on 2016 harvest produce after storage in a commercial storage facility for 5 months. The hyperspectral images were captured from either sides of apples in the range of 550⁻1700 nm. These images were analyzed to extract additional set of spectral features that were effective in bitter pit detection. Based on these features, an automated spatial data analysis algorithm was developed to detect bitter pit points. The pit area was extracted, and logistic regression was used to define the categorizing threshold. This method was able to classify the healthy and bitter pit apples with an accuracy of 85%. Finally, hyperspectral imagery derived spectral features were re-evaluated on the visible⁻near-infrared reflectance data acquired with spectrometer. The pertinent partial least square regression classification accuracies were in the range of 90⁻100%. Overall, the study identified salient spectral features based on both hyperspectral spectrometry and imaging techniques that can be used to develop a sensing solution to sort the fruit on the packaging lines.

Generalized analog thresholding for spike acquisition at ultralow sampling rates.

Efficient spike acquisition techniques are needed to bridge the divide from creating large multielectrode arrays (MEA) to achieving whole-cortex electrophysiology. In this paper, we introduce generalized analog thresholding (gAT), which achieves millisecond temporal resolution with sampling rates as low as 10 Hz. Consider the torrent of data from a single 1,000-channel MEA, which would generate more than 3 GB/min using standard 30-kHz Nyquist sampling. Recent neural signal processing methods based on compressive sensing still require Nyquist sampling as a first step and use iterative methods to reconstruct spikes. Analog thresholding (AT) remains the best existing alternative, where spike waveforms are passed through an analog comparator and sampled at 1 kHz, with instant spike reconstruction. By generalizing AT, the new method reduces sampling rates another order of magnitude, detects more than one spike per interval, and reconstructs spike width. Unlike compressive sensing, the new method reveals a simple closed-form solution to achieve instant (noniterative) spike reconstruction. The base method is already robust to hardware nonidealities, including realistic quantization error and integration noise. Because it achieves these considerable specifications using hardware-friendly components like integrators and comparators, generalized AT could translate large-scale MEAs into implantable devices for scientific investigation and medical technology.

Noise facilitation in associative memories of exponential capacity.

Recent advances in associative memory design through structured pattern sets and graph-based inference algorithms have allowed reliable learning and recall of an exponential number of patterns that satisfy certain subspace constraints. Although these designs correct external errors in recall, they assume neurons that compute noiselessly, in contrast to the highly variable neurons in brain regions thought to operate associatively, such as hippocampus and olfactory cortex. Here we consider associative memories with boundedly noisy internal computations and analytically characterize performance. As long as the internal noise level is below a specified threshold, the error probability in the recall phase can be made exceedingly small. More surprising, we show that internal noise improves the performance of the recall phase while the pattern retrieval capacity remains intact: the number of stored patterns does not reduce with noise (up to a threshold). Computational experiments lend additional support to our theoretical analysis. This work suggests a functional benefit to noisy neurons in biological neuronal networks.

The impact of COVID-19 lockdowns on mental health patient populations in the United States.

During the start of the COVID-19 pandemic in 2020, lockdowns and movement restrictions were thought to negatively impact population mental health, since depression and anxiety symptoms were frequently reported. This study investigates the effect of COVID-19 mitigation measures on mental health across the United States, at county and state levels using difference-in-differences analysis. It examines the effect on mental health facility usage and the prevalence of mental illnesses, drawing on large-scale medical claims data for mental health patients joined with publicly available state- and county-specific COVID-19 cases and lockdown information. For consistency, the main focus is on two types of social distancing policies, stay-at-home and school closure orders. Results show that lockdown has significantly and causally increased the usage of mental health facilities in regions with lockdowns in comparison to regions without such lockdowns. Particularly, resource usage increased by 18% in regions with a lockdown compared to 1% decline in regions without a lockdown. Also, female populations have been exposed to a larger lockdown effect on their mental health. Diagnosis of panic disorders and reaction to severe stress significantly increased by the lockdown. Mental health was more sensitive to lockdowns than to the presence of the pandemic itself. The effects of the lockdown increased over an extended time to the end of December 2020.

Pneumatic spray delivery-based fixed spray system configuration optimization for efficient agrochemical application in modern vineyards.

BACKGROUND: The hydraulic spray delivery (HSD)-based solid set canopy delivery system (SSCDS) emitter configuration has been optimized for agrochemical applications in vertical shoot position (VSP) vineyards. It uses cost-prohibitive emitters, and their placement restricts the mechanical pruning activities. Therefore, this study focused on optimizing the spray performance of a pneumatic spray delivery (PSD)-based SSCDS variant that addresses the earlier issues. Three PSD-SSCDS emitter configurations (C1-C3) were designed using modified low-cost emitters (E1: modified flat fan, E2: 90° modular flat fan) for agrochemical applications in VSP vineyards. C1 had an E1 installed on trellis posts at 1.67 m above ground level. C2 had a pair of E2 installed per vine at 0.3 m below the cordon, while C3 combined the emitter placement of C1 and C2. The spray deposition (ng cm-2) and coverage (%) were quantified (mean ± standard error) using mylar cards and water-sensitive paper samplers placed within the canopy, respectively. RESULTS: Spray deposition for C1, C2, and C3 was 301.12 ± 63.30, 347.9 ± 66.29, and 837.6 ± 92.53 ng cm-2, respectively. Whereas spray coverage for corresponding configurations was 18.02 ± 2.63, 8.98 ± 1.84, and 28.84 ± 2.46%, respectively. CONCLUSIONS: Overall, configuration C3 provided significantly higher spray deposition and coverage than C1 and C2. Substantially reduced system installation cost and emitter density per hectare with improved spray performance were achieved by C3 compared to earlier optimized HSD-SSCDS configuration in the VSP vineyards. © 2024 The Authors. Pest Management Science published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

The utilitarian brain: Moving beyond the Free Energy Principle.

The Free Energy Principle (FEP) is a normative computational framework for iterative reduction of prediction error and uncertainty through perception-intervention cycles that has been presented as a potential unifying theory of all brain functions (Friston, 2006). Any theory hoping to unify the brain sciences must be able to explain the mechanisms of decision-making, an important cognitive faculty, without the addition of independent, irreducible notions. This challenge has been accepted by several proponents of the FEP (Friston, 2010; Gershman, 2019). We evaluate attempts to reduce decision-making to the FEP, using Lucas' (2005) meta-theory of the brain's contextual constraints as a guidepost. We find reductive variants of the FEP for decision-making unable to explain behavior in certain types of diagnostic, predictive, and multi-armed bandit tasks. We trace the shortcomings to the core theory's lack of an adequate notion of subjective preference or "utility", a concept central to decision-making and grounded in the brain's biological reality. We argue that any attempts to fully reduce utility to the FEP would require unrealistic assumptions, making the principle an unlikely candidate for unifying brain science. We suggest that researchers instead attempt to identify contexts in which either informational or independent reward constraints predominate, delimiting the FEP's area of applicability. To encourage this type of research, we propose a two-factor formal framework that can subsume any FEP model and allows experimenters to compare the contributions of informational versus reward constraints to behavior.

Structural chokepoints determine the resilience of agri-food supply chains in the United States.

The agricultural and food systems of the United States are critical for ensuring the stability of both domestic and global food systems. Thus, it is essential to understand the structural resilience of the country's agri-food supply chains to a suite of threats. Here we employ complex network statistics to identify the spatially resolved structural chokepoints in the agri-food supply chains of the United States. We identify seven chokepoints at county scale: Riverside CA, San Bernardino CA, Los Angeles CA, Shelby TN, Maricopa AZ, San Diego CA and Cook IL; as well as seven chokepoints at freight analysis framework scale: Los Angeles-Long Beach CA, Chicago-Naperville IL, New York-New Jersey NJ, New York-New Jersey NY, Remainder of Texas, Remainder of Pennsylvania, and San Jose-San Francisco-Oakland CA. These structural chokepoints are generally consistent through time (2007, 2012, 2017), particularly for processed food commodities. This study improves our understanding of agri-food supply-chain security and may aid policies aimed at enhancing its resilience.

The State of Machine Learning in Outcomes Prediction of Transsphenoidal Surgery: A Systematic Review.

The purpose of this analysis is to assess the use of machine learning (ML) algorithms in the prediction of postoperative outcomes, including complications, recurrence, and death in transsphenoidal surgery. Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, we systematically reviewed all papers that used at least one ML algorithm to predict outcomes after transsphenoidal surgery. We searched Scopus, PubMed, and Web of Science databases for studies published prior to May 12, 2021. We identified 13 studies enrolling 5,048 patients. We extracted the general characteristics of each study; the sensitivity, specificity, area under the curve (AUC) of the ML models developed as well as the features identified as important by the ML models. We identified 12 studies with 5,048 patients that included ML algorithms for adenomas, three with 1807 patients specifically for acromegaly, and five with 2105 patients specifically for Cushing's disease. Nearly all were single-institution studies. The studies used a heterogeneous mix of ML algorithms and features to build predictive models. All papers reported an AUC greater than 0.7, which indicates clinical utility. ML algorithms have the potential to predict postoperative outcomes of transsphenoidal surgery and can improve patient care. Ensemble algorithms and neural networks were often top performers when compared with other ML algorithms. Biochemical and preoperative features were most likely to be selected as important by ML models. Inexplicability remains a challenge, but algorithms such as local interpretable model-agnostic explanation or Shapley value can increase explainability of ML algorithms. Our analysis shows that ML algorithms have the potential to greatly assist surgeons in clinical decision making.

Structural properties of the Caenorhabditis elegans neuronal network.

Despite recent interest in reconstructing neuronal networks, complete wiring diagrams on the level of individual synapses remain scarce and the insights into function they can provide remain unclear. Even for Caenorhabditis elegans, whose neuronal network is relatively small and stereotypical from animal to animal, published wiring diagrams are neither accurate nor complete and self-consistent. Using materials from White et al. and new electron micrographs we assemble whole, self-consistent gap junction and chemical synapse networks of hermaphrodite C. elegans. We propose a method to visualize the wiring diagram, which reflects network signal flow. We calculate statistical and topological properties of the network, such as degree distributions, synaptic multiplicities, and small-world properties, that help in understanding network signal propagation. We identify neurons that may play central roles in information processing, and network motifs that could serve as functional modules of the network. We explore propagation of neuronal activity in response to sensory or artificial stimulation using linear systems theory and find several activity patterns that could serve as substrates of previously described behaviors. Finally, we analyze the interaction between the gap junction and the chemical synapse networks. Since several statistical properties of the C. elegans network, such as multiplicity and motif distributions are similar to those found in mammalian neocortex, they likely point to general principles of neuronal networks. The wiring diagram reported here can help in understanding the mechanistic basis of behavior by generating predictions about future experiments involving genetic perturbations, laser ablations, or monitoring propagation of neuronal activity in response to stimulation.

Soil and Climate Geographic Information System Data-Derived Risk Mapping for Grape Phylloxera in Washington State.

Grape phylloxera (Daktulosphaira vitifoliae, syn. Viteus vitifoliae), a destructive root and foliar pest of grapevines, occurs in almost all viticulture regions worldwide. However, certain regions have remained "phylloxera free." Until recently, this included Washington state (United States), where this insect is regulated as a quarantine pest by Washington State Department of Agriculture. In 2019, established phylloxera populations were discovered in Washington. Phylloxera is typically managed by using resistant or tolerant rootstocks. In Washington, most wine grapes are grown on their own roots of the susceptible species Vitis vinifera instead of grafted rootstock, and thus, are at high risk of vine death should they become infested with phylloxera. This article reports development of a phylloxera risk map for Washington state using geographical soil texture (sand content) and soil temperature data. Weighted averages of soil texture data (mapping year: 2016, depth: 0-100 cm) were obtained from United States Department of Agriculture-Natural Resource Conservation Service (USDA-NRCS) and soilgrids. Soil temperature data were obtained from over 200 weather stations of Washington State University's AgWeatherNet network. Threshold-based classifications were performed in Quantum GIS software on the rasterized soil sand content and temperature independently to derive low, moderate, and high-risk areas, with risk defined as site suitability for optimal phylloxera development. The validation identified 22 out of 23 confirmed phylloxera-positive sites as "high risk," and one site as "moderate risk" when considering soil sand content alone. Soil temperature data alone classified 10 sites as "high risk" and 13 sites as "low risk." When soil sand content was combined with soil temperature (as a risk modifier), 10 sites were classified as "high risk," 12 sites as "high-moderate risk" and one site as "moderate-low" risk. Ground-truth comparisons of confirmed positive sites for phylloxera agreed with past research suggesting that soil sand content is the dominant factor influencing phylloxera infestation. Pertinent risk assessment can be an important component for vineyard decision-making, including whether to use rootstocks in vineyard development or replant scenarios. It may also help to focus the initial scouting and identification efforts to sites and may be helpful when tracking and developing solutions for quarantine pests, such as phylloxera.

Identification of volatile biomarkers for high-throughput sensing of soft rot and Pythium leak diseases in stored potatoes.

Soft rot and Pythium leak are postharvest storage diseases of potato tubers that can cause substantial crop losses in the US. This study focused on detecting volatile organic compounds (VOCs) associated with rot inoculated tubers during storage (up to 21 days) using headspace solid-phase microextraction (SPME) coupled to gas chromatography (GC) with mass spectrometry (MS) and flame ionization detector (FID) analysis. Russet Burbank and Ranger Russet tubers were inoculated with the rot pathogens. Static sampling with 50 min trapping time followed by GC-MS and GC-FID analysis identified 23 and 30 common VOCs from the pathogen inoculated tubers. Overall, n,n-dimethylmethylamine, acetone, 1-undecene, and styrene, occurred frequently and repeatability in inoculated samples based on GC-MS analysis, with the latter two found using GC-FID analysis as well. Identification of such biomarkers can be useful in developing high-throughput VOC sensing systems for early disease detection in potato storage facilities.

Pneumatic spray delivery-based solid set canopy delivery system for oblique banded leaf roller and codling moth control in a high-density modern apple orchard.

BACKGROUND: Pneumatic spray delivery (PSD)-based solid set canopy delivery systems (SSCDS) have demonstrated comparable spray deposition and reduced off-target drift compared with axial-fan airblast sprayers in high-density apple orchards. An important next step is to quantify whether PSD-based SSCDS can provide effective pest management. This study evaluated the biological efficacy of this fixed spray system variant and compared it with that of an axial-fan airblast sprayer. Partial field trials were conducted in a commercial apple orchard (cv. Jazz) trained in tall spindle architecture. Insecticides were applied at a rate of 935 L ha-1 (100 gallons per acre) for both application systems. Twenty-four hours after spraying, leaves and fruits were collected to prepare the laboratory bioassays enabling evaluation of efficacy against obliquebanded leafroller (OBLR) and codling moth (CM). RESULTS: OBLR mortality for SSCDS, airblast sprayer and untreated control treatments after 24 h of larval exposure was 91%, 98% and 4%, respectively and increased to 98%, 100% and 19% after 48 h. First-instar CM leaf bioassay mortality was 100% for SSCDS and airblast sprayer treatment, and 13% for the untreated control at 24 h post exposure. Larval CM mortality on fruit was 100% for SSCDS and airblast sprayer treatments, and 33% on the untreated control. CONCLUSIONS: Insecticides applied using SSCDS and an airblast sprayer had comparable larval mortality in all three assays, significantly higher than the untreated controls. These results suggest that PSD-based SSCDS may provide a viable alternative to axial-fan airblast sprayers in high-density apple orchards. © 2022 The Authors. Pest Management Science published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

Social capital dimensions are differentially associated with COVID-19 vaccinations, masks, and physical distancing.

BACKGROUND: Social capital has been associated with health outcomes in communities and can explain variations in different geographic localities. Social capital has also been associated with behaviors that promote better health and reduce the impacts of diseases. During the COVID-19 pandemic, social distancing, face masking, and vaccination have all been essential in controlling contagion. These behaviors have not been uniformly adopted by communities in the United States. Using different facets of social capital to explain the differences in public behaviors among communities during pandemics is lacking. OBJECTIVE: This study examines the relationship among public health behavior-vaccination, face masking, and physical distancing-during COVID-19 pandemic and social capital indices in counties in the United States. METHODS: We used publicly available vaccination data as of June 2021, face masking data in July 2020, and mobility data from mobile phones movements from the end of March 2020. Then, correlation analysis was conducted with county-level social capital index and its subindices (family unity, community health, institutional health, and collective efficacy) that were obtained from the Social Capital Project by the United States Senate. RESULTS: We found the social capital index and its subindices differentially correlate with different public health behaviors. Vaccination is associated with institutional health: positively with fully vaccinated population and negatively with vaccination hesitancy. Also, wearing masks negatively associates with community health, whereases reduced mobility associates with better community health. Further, residential mobility positively associates with family unity. By comparing correlation coefficients, we find that social capital and its subindices have largest effect sizes on vaccination and residential mobility. CONCLUSION: Our results show that different facets of social capital are significantly associated with adoption of protective behaviors, e.g., social distancing, face masking, and vaccination. As such, our results suggest that differential facets of social capital imply a Swiss cheese model of pandemic control planning where, e.g., institutional health and community health, provide partially overlapping behavioral benefits.

Beyond IQ: The Importance of Metacognition for the Promotion of Global Wellbeing.

Global policy makers increasingly adopt subjective wellbeing as a framework within which to measure and address human development challenges, including policies to mitigate consequential societal problems. In this review, we take a systems-level perspective to assemble evidence from studies of wellbeing, of collective intelligence, and of metacognition and argue for a virtuous cycle for health promotion in which the increased collective intelligence of groups: (1) enhances the ability of such groups to address consequential societal problems; (2) promotes the wellbeing of societies and the individual wellbeing of people within groups; and, finally, (3) enables prosocial actions that further promote collective problem-solving and global wellbeing. Notably, evidence demonstrates that effective collaboration and teamwork largely depend on social skills for metacognitive awareness-the capacity to evaluate and control our own mental processes in the service of social problem-solving. Yet, despite their importance, metacognitive skills may not be well-captured by measures of general intelligence. These skills have instead been the focus of decades of research in the psychology of human judgment and decision-making. This literature provides well-validated tests of metacognitive awareness and demonstrates that the capacity to use analysis and deliberation to evaluate intuitive responses is an important source of individual differences in decision-making. Research in network neuroscience further elucidates the topology and dynamics of brain networks that enable metacognitive awareness, providing key targets for intervention. As such, we further discuss emerging scientific interventions to enhance metacognitive skills (e.g., based on mindfulness meditation, and physical activity and aerobic fitness), and how such interventions may catalyze the virtuous cycle to improve collective intelligence, societal problem-solving, and global wellbeing.

Optimal information storage in noisy synapses under resource constraints.

Experimental investigations have revealed that synapses possess interesting and, in some cases, unexpected properties. We propose a theoretical framework that accounts for three of these properties: typical central synapses are noisy, the distribution of synaptic weights among central synapses is wide, and synaptic connectivity between neurons is sparse. We also comment on the possibility that synaptic weights may vary in discrete steps. Our approach is based on maximizing information storage capacity of neural tissue under resource constraints. Based on previous experimental and theoretical work, we use volume as a limited resource and utilize the empirical relationship between volume and synaptic weight. Solutions of our constrained optimization problems are not only consistent with existing experimental measurements but also make nontrivial predictions.

Generalized Linear Model with Elastic Net Regularization and Convolutional Neural Network for Evaluating Aphanomyces Root Rot Severity in Lentil.

Phenomics technologies allow quantitative assessment of phenotypes across a larger number of plant genotypes compared to traditional phenotyping approaches. The utilization of such technologies has enabled the generation of multidimensional plant traits creating big datasets. However, to harness the power of phenomics technologies, more sophisticated data analysis methods are required. In this study, Aphanomyces root rot (ARR) resistance in 547 lentil accessions and lines was evaluated using Red-Green-Blue (RGB) images of roots. We created a dataset of 6,460 root images that were annotated by a plant breeder based on the disease severity. Two approaches, generalized linear model with elastic net regularization (EN) and convolutional neural network (CNN), were developed to classify disease resistance categories into three classes: resistant, partially resistant, and susceptible. The results indicated that the selected image features using EN models were able to classify three disease categories with an accuracy of up to 0.91 ± 0.004 (0.96 ± 0.005 resistant, 0.82 ± 0.009 partially resistant, and 0.92 ± 0.007 susceptible) compared to CNN with an accuracy of about 0.84 ± 0.009 (0.96 ± 0.008 resistant, 0.68 ± 0.026 partially resistant, and 0.83 ± 0.015 susceptible). The resistant class was accurately detected using both classification methods. However, partially resistant class was challenging to detect as the features (data) of the partially resistant class often overlapped with those of resistant and susceptible classes. Collectively, the findings provided insights on the use of phenomics techniques and machine learning approaches to provide quantitative measures of ARR resistance in lentil.

Prediction of odor complaints at a large composite reservoir in a highly urbanized area: A machine learning approach.

Odorous compound emissions and odor complaints from the public are rising concerns for agricultural, industrial, and water resource recovery facilities (WRRFs) near urban areas. Many facilities are deploying sensors that measure malodorous compounds and other factors related to odor creation and dispersion. Focusing on the Metropolitan Water Reclamation District of Greater Chicago's (MWRDGCs) Thornton Composite Reservoir (7.9 billion gallon capacity), we used meteorological, operational, and H2S sensor data to train a 3-day advance-warning predictor of local odor complaints, so as to implement targeted odor prevention measures. Using a machine learning approach, we bypassed difficulties in modeling both physical dispersion and human perception of odors. Utilizing random forest algorithms with varied settings and input attributes, we find that a small network of H2S sensors, meteorological data, and operational data are able to predict odor complaints three days in advance with greater than 60% accuracy and less than 25% false-positive rates, exceeding MWRDGC's standards required for full-scale deployment. PRACTITIONER POINTS: A random forest algorithm trained on H2 S, weather, and operations data successfully predicted odor complaints surrounding a large composite reservoir. Thirty-two data attribute combinations were tested. It was found that H2 S sensor data alone are insufficient for predicting odor complaints. The best predictor was a Random Forest Classifier trained on weather, operational, and H2 S readings from the reservoir corner locations. This study demonstrates odor complaint prediction capability utilizing a limited set of data sources and open-source machine learning techniques. Given a small network of H2 S sensors and organized data management, WRRFs and similar facilities can conduct advance-warning odor complaint prediction.