Decision-making Process Research Articles

Decision-making process regarding safety and crisis management for childcare workers: Focusing on food allergy management

When it comes to childcare, parents want to rest assured that, in their absence, their children are being provided with engaging activities, balanced nutrition and safety. Awareness of food allergies is key in childcare settings but most childcare workers donâ–™t have medical backgrounds and therefore staff training on food allergies and related crises is imperative. Kayo Tamura is a former childcare worker and lecturer at Aichi Gakusen University in Japan who is developing guidelines for decision making processes for food allergy and crisis management for childcare workers. Guidelines were implemented by the Japanese Government following incidents involving allergies and school lunches in 1988 and 2012. However, Tamura is concerned that some teachers and childcare workers may be unable to implement these, meaning that accidents will continue to occur. Therefore, she is working with childcare providers to better understand how guidelines and training are received and implemented in childcare settings. In order to assess how much knowledge about food allergies and sense of crisis awareness students have developed by graduation, Tamara conducted a questionnaire survey of university students studying childcare. She also conducted a survey using the same questions, this time posed to childcare workers and performed a statistical analysis of the results. She found that many students already had some awareness of food allergies, often through personal experience but they acquired more specialist knowledge through university by reviewing government guidelines and manuals and through childcare training.

The Role of Artificial Intelligence in Bariatric Surgery: Perspectives and Modern Applications

<p dir="ltr"><span>Artificial intelligence (AI) is having a major impact in the field of bariatric surgery (BS) as it helps improve outcomes for patients with severe obesity. This advanced technology optimises clinical decision-making processes and helps reduce the risks associated with surgery. In the context of bariatrics, AI is used to identify suitable patients, and monitor postoperative recovery but also to predict complications that may occur. BS is an effective solution for treating severe obesity, a condition characterised by the excessive accumulation of body fat, which can lead to serious health problems. However, this surgical field faces challenges in terms of patient selection and follow-up. By implementing machine learning (ML) algorithms and advanced imaging technologies, AI offers advantages to surgeons in performing interventions with increased precision and efficiency. The integration of AI into BS brings significant benefits to both patients and healthcare professionals, thereby facilitating the development of a personalised and safe approach to obesity management. Through this review, we aim to explore the potential, benefits, and risks of using AI in the context of BS.</span></p>

Demystifying the Relationship between Digitalization of Government Services and Public Trust: A Scoping Review

Citizen trust is critical for effective public policy implementation. However, according to a recent report from the OECD, only 39% of citizens have medium or high trust in the government. Among others, the use of digital technology has been considered to foster public trust by leveraging the transparency of government data, information, or decision-making process. The purpose of this scoping review is to provide an overview of the relationship between digitalization of government services and public trust using the Arksey and O'Malley methodological framework. Based on the technology, organization, and environment (TOE) framework, individual, and trust aspect, this study identifies and categorizes 112 distinct constructs mapped across five key contexts: technology, organization, environment, individual, and trust. The study findings help to improve our previously limited understanding of the relationship between digitalization of government services and trust by identifying a set of concepts related to each of six research contexts that may prove fruitful in our efforts to develop theory explaining this key e-government relationship. Furthermore, from the practical aspect, it provides insights for the public administrators and policymakers that should be considered when developing effective public policies regarding digitalization and public trust.

Drivers of Merger and Acquisition Activities in Vietnam: Insights from Targets’ Perspectives and Deal Characteristics

This study empirically examines the determinants of merger and acquisition (M&A) activities in Vietnam from 2005 to 2020, which has not been examined before, using a fixed-effects model for a sample of 674 completed M&A deals. The results indicate that targets’ corporate governance and deal characteristics have mixed effects on M&A decisions. More specifically, the independent member of the board and CEO duality of the target is negatively associated with most M&A types, except for cross-border mergers. However, the impact of targets’ blockholders is consistently positive regardless of M&A types. When observing the deal characteristics, mixed evidence is also found in the case of M&A payment form, industry-relatedness between the bidder and the target, the bidder’s stake in the target, and foreign ownership in the bidder’s stake. More interesting, our study emphasizes that voluntary agreement is seemingly critical to M&A decisions regardless of different types. Our results suggest several important implications, including balancing independent directors on the board, accounting for CEOs’ and other blockholders’ interests and influence, considering the types of M&A payments, and involving foreign investors in M&A activities. By understanding these implications, firms can better navigate the complexities of M&A transactions, enhancing their decision-making processes and ultimately contributing to improved shareholder value.

Integrating environmental sustainability into the teaching of global health ethics from a students’ perspective: new guiding questions

ABSTRACT Environmental sustainability stands out as a crucial topic in global health. Although this concept has been part of ethical discussions for over two decades, progress toward its adoption within global health ethics education remains slow and hesitant, hindering its integration into global health practice and decision-making processes. As recent global health graduates, we believe that global health relies on the interconnectedness of human and environmental health. Therefore, we sought to address a gap in our ethics formation by proposing the inclusion of an environmental sustainability perspective in global health ethics teaching through a revised question checklist and classroom activity. This question checklist expands on the seven teaching principles for public health ethics by Schröder-Bäck et al. applying an environmental ethics lens to global health ethics. The group activity offers a structured method for students to explore practical applications of environmental sustainability in global health processes. We aim to foster more critical reflections and discussions on this topic among future global health professionals and students, paving the way for a more environmentally sustainable future in global health.

Patient autonomy and metabolic bariatric surgery: an empirical perspective

BackgroundMetabolic Bariatric Surgery (MBS) has gained significant popularity over the past decade. Legally and ethically, physicians should obtain the patient’s voluntary and informed consent before proceeding with the surgery. However, the decision to undergo MBS is often influenced by external factors, prompting questions about their impact on the patient’s ability to choose voluntarily.In addressing this issue, the study focuses on two key questions: first, which factors influence MBS candidates during the decision-making process, and second, whether these influences undermine the candidates' ability to make decisions voluntarily, according to theories of autonomy.MethodsThe study employed a qualitative methodology, conducting 21 in-depth semi-structured interviews with adults who had undergone bariatric surgery. The conclusions were drawn from an inductive analysis of the interview data conducted using a grounded theory approach, and by applying theories of autonomy to the empirical findings.ResultsOur study indicates that interviewees were exposed to different external influences, which had diverse effects on the interviewees' decision to undergo MBS.Category 1 influences included intentional attempts to induce people, through arguments and reason, to accept the attitudes advocated by the persuader in support of the surgery. Applying theoretical accounts of autonomy to these influences suggests that they did not compromise the interviewees’ autonomy.Category 2 influences included threats made by a physician or a family member. These influences were found to undermine autonomy.Category 3 influences included emotional manipulation, informational manipulation, and the construction of medical and social norms. Manipulations and norms were experienced differently by different interviewees, and their impact on autonomy varies depending on the theoretical framework applied.ConclusionsAcknowledging that the influences exerted on MBS candidates may undermine their ability to make autonomous decisions regarding surgery, we suggest reformulating the duties that apply to medical practitioners with respect to informed consent to MBS.Medical practitioners who discuss the option of MBS with candidates should be aware of the various factors that influence this choice, and actively promote the candidates’ ability to make autonomous decisions.

Reinforcement learning in women remitted from anorexia nervosa: Preliminary examination with a hybrid reinforcement learning/drift diffusion model.

Altered reinforcement learning (RL) and decision-making have been implicated in the pathophysiology of anorexia nervosa. To determine whether deficits observed in symptomatic anorexia nervosa are also present in remission, we investigated RL in women remitted from anorexia nervosa (rAN). Participants performed a probabilistic associative learning task that involved learning from rewarding or punishing outcomes across consecutive sets of stimuli to examine generalization of learning to new stimuli over extended task exposure. We fit a hybrid RL and drift diffusion model of associative learning to model learning and decision-making processes in 24 rAN and 20 female community controls (cCN). rAN showed better learning from negative outcomes than cCN and this was greater over extended task exposure (p < .001, ηp2 = .30). rAN demonstrated a reduction in accuracy of optimal choices (p = .007, ηp2 = .16) and rate of information extraction on reward trials from set 1 to set 2 (p = .012, ηp2 = .14), and a larger reduction of response threshold separation from set 1 to set 2 than cCN (p = .036, ηp2 = .10). rAN extracted less information from rewarding stimuli and their learning became increasingly sensitive to negative outcomes over learning trials. This suggests rAN shifted attention to learning from negative feedback while slowing down extraction of information from rewarding stimuli. Better learning from negative over positive feedback in rAN might reflect a marker of recovery.

Consensus based sustainable decision making using probability hesitant fuzzy preference relations with application on risk assessment in food industry

This paper describes a consensus-based approach for dealing with multi-person decision-making problems which incorporate probability hesitant fuzzy preference relations. The procedure begins with establishing expected fuzzy preference relations based on the delivered hesitant fuzzy preference relations using a probabilistic aggregation approach, providing the platform for the framework to make decisions. Then, a multiplicative transitive closure formula is defined to construct multiplicative consistent expected fuzzy preference relations and symmetrical matrices, ensuring the reliability of the preference relations. Following that, a consistency analysis is undertaken to assess the consistency levels of the information provided by experts, allowing them to be assigned information priority weights while also guaranteeing that their inputs are balanced and reliable. In order to make sure that all pertinent factors are taken into account during the decision-making process, the ultimate priority weights for the experts are determined through the combination of consistency-based weights with any specified priority weights, if applicable. The consensus process eventually decides whether to aggregate the data and choose the optimal option based on the collective inputs. To strengthen the experts’ consensus measure, an enhancement method is provided that detects weak viewpoints in cases of poor consensus and allows for targeted modifications. To highlight the suggested scheme’s practicality and usefulness, a comparison example is provided, with results indicating that the method provides valuable insights into the multi-person decision-making process, making it a potential option for achieving agreement in complicated decision-making settings.

Deep learning and explainable AI for classification of potato leaf diseases

The accurate classification of potato leaf diseases plays a pivotal role in ensuring the health and productivity of crops. This study presents a unified approach for addressing this challenge by leveraging the power of Explainable AI (XAI) and transfer learning within a deep Learning framework. In this research, we propose a transfer learning-based deep learning model that is tailored for potato leaf disease classification. Transfer learning enables the model to benefit from pre-trained neural network architectures and weights, enhancing its ability to learn meaningful representations from limited labeled data. Additionally, Explainable AI techniques are integrated into the model to provide interpretable insights into its decision-making process, contributing to its transparency and usability. We used a publicly available potato leaf disease dataset to train the model. The results obtained are 97% for validation accuracy and 98% for testing accuracy. This study applies gradient-weighted class activation mapping (Grad-CAM) to enhance model interpretability. This interpretability is vital for improving predictive performance, fostering trust, and ensuring seamless integration into agricultural practices.

Moral sensitivity and attitudes towards patient safety among critical care nurses.

Patient safety is essential for healthcare quality and a global concern. The rapid advancement of medical technology presents ethical challenges for critical care nurses, who navigate complex decision-making processes. Given their close relationships with patients, nurses are uniquely positioned to address patient safety issues. Thus, enhancing nurses' moral sensitivity and ethical values is increasingly important. This study aims to explore the relationship between moral sensitivity and attitude towards patient safety in critical care nurses. This cross-sectional, descriptive-correlational study was conducted from June to September 2022 in three hospitals affiliated with Hamadan University of Medical Sciences in Iran. Participants were nurses in intensive care units (ICUs), selected via convenience sampling. A total of 382 nurses completed questionnaires assessing demographic information, moral sensitivity, and patient safety attitudes. Data analysis was performed using descriptive statistics, t-tests, ANOVA, Pearson's correlation, and multiple regression in SPSS 26.Ethical considerations: This research received ethical approval from the Ethics Committee of Hamadan University of Medical Sciences. Participants provided informed consent regarding the study's objectives, and their confidentiality was strictly upheld throughout the research. The nurses' average age and work experience were 38.6years and 12.4years, respectively. Mean scores for moral sensitivity and patient safety attitude were 81.65 ± 2.69 and 51.47 ± 2.21, indicating high levels and a significant positive correlation. Factors such as increasing age, work experience, fewer working hours, and completion of ethics training were linked to more positive attitudes towards patient safety (p < .05). Regression analysis showed that 42.8% of the variability in attitudes towards patient safety could be explained by moral sensitivity and demographic characteristics. This study highlights the relationship between moral sensitivity and patient safety attitudes among critical care nurses, emphasizing the importance of education, experience, and training in shaping ethical values. Enhancing moral sensitivity is vital for reducing risky behaviors and improving patient safety outcomes in critical care settings.

Do mental health professionals react to verbal aggressiveness differently if it is gender-related? An experimental study employing case-vignettes

Background Gender bias in the comprehension and management of violent behaviour in mental health settings remains a contentious issue. Aims This study examines how gender-related verbal aggressiveness influences the clinical judgment and decision-making processes of mental health professionals (MHPs). Methods Four vignettes depicting confrontations between MHPs and service users were created, varying by the service user’s gender and whether verbal aggression was gender related. Within an experimental design, a total of 110 MHPs were randomly assigned to vignettes featuring a service user of the opposite gender. Participants completed assessments on clinical judgment, symptomatology, and personal beliefs. Results Gender-related verbal aggressiveness influenced clinical judgment, with male professionals demonstrating greater sensitivity to these conditions compared to their female counterparts. Female MHPs exhibited more consistent evaluations across experimental conditions. Gender-specific patterns in symptomatology assignment were observed. Conclusions These findings highlight the influence of gender role expectations and sociocultural factors on clinical judgments, which may reinforce gender biases in mental health assessments. Awareness of these biases and targeted training could enhance equitable and unbiased care.

A Methodology for the Feasibility Assessment of Using Crop Residues for Electricity Production Through GIS-MCD and Its Application in a Case Study

Over recent decades, human activities have essentially depended on fossil fuels. The last Intergovernmental Panel on Climate Change reports recommend a shift to renewables and a more energy-efficient economy. To fulfill the potential of bioenergy, tools are required to overcome the complexities of the decision-making processes for viable projects. This work presents a decision-making tool to select the most feasible biomass residues and a case study of the state of Minas Gerais, in Brazil. Among the 13 evaluated criteria, eucalyptus residues demonstrated the highest potential for electricity production, followed by sugarcane bagasse and coffee husks. The choice of Minas Gerais as a case study is important due to its diverse agricultural landscape and the potential for biomass residue generation. The presented methodology uses the Analytical Hierarchy Process (AHP), a multi-criteria decision-making method (MCDM). Thirteen criteria were required to enable the best choice of biomass residue alternatives for electricity generation, which experts in the bioenergy field evaluated. The technical criterion was shown to be the one with the highest degree of importance. The results of the study identified that CO2eq emissions (11.46%) and electricity demand (ED) were the most relevant sub-criteria for prioritizing the viability of agricultural waste. Eucalyptus was ranked as the most promising biomass, followed by sugarcane bagasse and coffee husks. In addition, the use of GIS tools made it possible to map the regions with the greatest potential in Minas Gerais, providing a robust approach to identifying strategic sites for bioenergy.

Challenges and Opportunities in Malawian Education: Focusing on Teacher Training

The primary education system in Malawi experienced significant changes, especially since the abolition of school fees in 1994, which resulted in an instant surge in enrolments. However, access improvements have not translated into substantial gains in educational quality. The primary education sector in Malawi is still under constant pressure and facing numerous challenges. The most important factors that need attention are the inadequate infrastructure, high pupil-teacher ratios and the lack of trained teachers. Financial constraints, such as allocating budgets to teacher salaries and inefficiencies in using School Improvement Grants (SIGs), further hinder progress. Systematic challenges are related to expenditure allocations, educational outcomes and service deliveries. Despite these challenges, there are opportunities to improve educational outcomes through targeted interventions. In-service training programs, like the Primary School Improvement Program (PSIP) and Technology-Assisted Learning (TAL), have demonstrated some positive impacts, especially in enhancing teacher practices and learning environments. Practical teacher training and ICT integration catalyse change in a resource-constrained environment. This paper also discusses recommendations for policy reforms, including better allocation of SIGs, optimising teacher deployment, and enhancing community involvement in school decision-making processes to evoke and strengthen ownership and responsibility outside of the school walls. Addressing the comprehensive inefficiencies requires a multifaceted approach that includes greater accountability in resource use, enhanced teacher support, and more equitable resource distribution across urban and rural schools. Recognising and addressing the unique challenges of the different schools in different areas is crucial. Focusing on cost-effective strategies and leveraging partnerships with international donors can also significantly reshape Malawi's education system. Ultimately, improving teacher quality and ensuring effective service delivery is essential for enhancing learning outcomes and addressing the persistent issues in the education sector in Malawi.

Towards Streamlining the Choice of Crossing Combinations in Plant Breeding by Integrating Model-Based Recommendations and Plant Breeder’s Preferences

Selecting crossing combinations crucial for successfully developing new improved crop varieties and genomic data from DNA markers have become invaluable for guiding plant breeders in evaluating and choosing promising crosses between potential parents. However, navigating the vast array of thousands of possible parental combinations, even with extensive genomic information, can be challenging, even for experienced breeders with deep knowledge of their crop’s gene pool. This case study aimed to evaluate the effectiveness of a recommender system to support plant breeders in this complex decision-making process. It took a retrospective approach, analyzing selection decisions made by an experienced breeder across several thousand potential crossing combinations over six years. The results indicated that a recommender system could significantly reduce the time and effort needed to identify promising crosses aligned with the breeder’s preferences. However, active feedback from the breeder to the recommender system appeared to be essential for achieving a satisfactory prediction. Integrating model-based recommendations and plant breeder’s preferences in a recommender system featuring such a reciprocal fine-tuning scheme, where the breeder actively provides feedback to the machine in the style of hybrid human–artificial intelligence, represents one step towards streamlining the choice of crossing combinations in plant breeding programs.

Pengaruh Kualitas Produk, Promosi, dan Citra Merek Terhadap Keputusan Pembelian Sepeda Motor Studi pada Dealer Motor Honda PT. Tirto Agung Porong

The purpose of this study was to analyze the influence of product quality, brand image, and price perception on the consumer decision-making process for purchasing Honda motorcycles. The population of this study consists of all residents of Sidoarjo. The sample was determined using the Lameshow formula, resulting in a sample size of 96.04, which was rounded up to 100 respondents. This study employed a non-probability sampling technique, specifically accidental sampling. The variables studied include product quality, promotion, and brand image. The t-test results show that product quality has a positive and significant effect on motorcycle purchasing decisions, promotion has a positive and significant effect on motorcycle purchasing decisions, and brand image also has a positive and significant effect on motorcycle purchasing decisions at the Tirto Agung Porong Dealership.

A data-and-knowledge-driven framework for automated generation of asphalt pavement maintenance strategies

ABSTRACT Due to the inefficiency of manual decision-making, automation of pavement maintenance strategy-making (PMSM) has become a focal point of attention in pavement engineering. The current automated PMSM processes lack a framework capable of integrating engineering prior knowledge into decision. In this paper, a data-and-knowledge-driven (DKD) framework was proposed to achieve the automated generation of asphalt pavement maintenance strategies. A pavement performance prediction model Convolutional Neural Network (CNN) was trained considering multiple influencing factors to analyse pavement deterioration, and maintenance thresholds were set according to predicted performance data distribution. The model incorporating Bidirectional Encoder Representations from Transformers (BERT), Bidirectional Long-Short-Term Memory (Bi-LSTM) and Conditional Random Field (CRF) was employed to extract the name entities from pavement maintenance domain knowledge, constructing the knowledge graph to achieve maintenance treatment determination. A freeway in Eastern China was selected for case study. The result demonstrated that 87 one-hundred-meter pavement sections on the freeway need preventive maintenance totally, utilising micro-surfacing in 2023. Furthermore, a level of automation assessment method and a reasonableness of decision process assessment method were proposed to assess this framework. The results indicate that this framework significantly enhances the level of automation compared to traditional PMSM methods while maintaining decision reasonableness.

An Oracle-Guided Approach to Constrained Policy Synthesis Under Uncertainty

Dealing with aleatoric uncertainty is key in many domains involving sequential decision making, e.g., planning in AI, network protocols, and symbolic program synthesis. This paper presents a general-purpose model-based framework to obtain policies operating in uncertain environments in a fully automated manner. The new concept of coloured Markov Decision Processes (MDPs) enables a succinct representation of a wide range of synthesis problems. A coloured MDP describes a collection of possible policy configurations with their structural dependencies. The framework covers the synthesis of (a) programmatic policies from probabilistic program sketches and (b) finite-state controllers representing policies for partially observable MDPs (POMDPs), including decentralised POMDPs as well as constrained POMDPs. We show that all these synthesis problems can be cast as exploring memoryless policies in the corresponding coloured MDP. This exploration uses a symbiosis of two orthogonal techniques: abstraction refinement—using a novel refinement method—and counter-example generalisation. Our approach outperforms dedicated synthesis techniques on some problems and significantly improves an earlier version of this framework.

PRG4CNN: A Probabilistic Model Checking-Driven Robustness Guarantee Framework for CNNs

As an important kind of DNN (deep neural network), CNN (convolutional neural network) has made remarkable progress and been widely used in the vision and decision-making of autonomous robots. Nonetheless, in many scenarios, even a minor perturbation in input for CNNs may lead to serious errors, which means CNNs lack robustness. Formal verification is an effective method to guarantee the robustness of CNNs. Existing works predominantly concentrate on local robustness verification, which requires considerable time and space. Probabilistic robustness quantifies the robustness of CNNs, which is a practical mode of potential measurement. The state-of-the-art of probabilistic robustness verification is a test-driven approach, which is used to manually decide whether a DNN satisfies the probabilistic robustness and does not involve robustness repair. Robustness repair can improve the robustness of CNNs further. To address this issue, we propose a probabilistic model checking-driven robustness guarantee framework for CNNs, i.e., PRG4CNN. This is the first automated and complete framework for guaranteeing the probabilistic robustness of CNNs. It comprises four steps, as follows: (1) modeling a CNN as an MDP (Markov decision processes) by model learning, (2) specifying the probabilistic robustness of the CNN via the PCTL (Probabilistic Computational Tree Logic) formula, (3) verifying the probabilistic robustness with a probabilistic model checker, and (4) probabilistic robustness repair by counterexample-guided sensitivity analysis, if probabilistic robustness does not hold on the CNN. We here conduct experiments on various scales of CNNs trained on the handwriting dataset MNIST, and demonstrate the effectiveness of PRG4CNN.

A Blockchain-based Landslide Mitigation Recommendation System for Decision-Making

Landslides are catastrophic natural disasters that could threaten the structural integrity of a building, imposing hazards to engineering and human life. This study proposes a TOPSIS landslide disaster mitigation recommendation system integrated with blockchain. New approaches to data provenance, transparency, and informed decision-making are explored in the context of geospatial blockchain. The decision-making process is carried out using the multicriteria evaluation method, which considers soil stability, rainfall, vegetation density, proximity to rivers, and slope. The results yielded promising precision, recall, accuracy, and F1 scores (91%, 93%, 95%, and 95%, respectively), suggesting that the model could make accurate and impartial prioritization predictions. Blockchain ensures data transparency, immutability, and security, and TOPSIS ranks mitigation strategies from worst to best to determine the better solution. The proposed approach is essential to predict regions that are prone to landslides and enables the appropriate management of relaxation measures. This application of blockchain technology can provide trust, reliability, and speed in decision-making while reducing landslides.

A Comparative Study of Fine-Tuning Deep Learning Models for Leaf Disease Identification and Classification

Innovative agricultural solutions are needed to detect and classify leaf diseases early across crop species and environments. This study compares deep learning approaches, focusing on Convolutional Neural Networks (CNN) and Vision Transformers (VTs), to identify leaf diseases early and accurately for scalable crop management and productivity. Optimizing CNNs, Explainable Transfer Learning (ETPLDNet) using ResNet50 architecture, and LEViT leaf disease diagnosis are compared. The CNN model, optimized with dynamic hyperparameters, achieved an impressive 99.58% accuracy for leaf disease classification, demonstrating its effectiveness in feature extraction and classification precision. On the other hand, the VT-based LEViT model, which leverages self-attention mechanisms and Explainable AI (XAI), achieved 95.22% accuracy but offers enhanced interpretability and generalization capabilities due to its transformer-based architecture. This distinction illustrates that while CNNs excel in accuracy, VTs provide a more transparent decision-making process and better handle the complex variances in plant leaf diseases, making them ideal for precision agriculture. The combined use of CNNs and VTs showcases the strengths of each model, with CNN focusing on high classification precision and VTs offering improved interpretability and adaptability for various leaf disease conditions. The use of XAI enables the models to highlight important areas in plant leaf images that influence the model's decisions, offering a transparent and interpretable decision-making process that allows researchers and farmers to understand why a particular diagnosis or classification was made. This ability to visualize and explain the reasoning behind the model predictions is crucial to increasing trust in AI-driven solutions in agriculture. By combining the high precision of CNN and the interpretability of VT with XAI, this study offers a robust approach to improving crop disease management and precision agriculture.