Disease prediction models in plant pathology: Leveraging ai and machine learning for early intervention

Introduction

The agricultural sector is a cornerstone of global food security and economic stability. However, plant diseases present a persistent challenge, causing significant crop losses and threatening the livelihoods of farmers. These diseases are often caused by a variety of pathogens, including fungi, bacteria, viruses, and nematodes, and are exacerbated by changing environmental conditions. Accurate and timely detection of plant diseases is critical to minimizing their impact. Yet, traditional methods for disease detection and management are often insufficient in addressing the scale and complexity of modern agricultural systems [1][2][3][4] . Conventional approaches rely on human expertise to observe symptoms, conduct laboratory tests, and implement control measures. While effective to some extent, these methods have several limitations. First, manual observation and diagnosis are time-intensive and prone to human error, particularly in cases where symptoms are ambiguous or similar to those of other stressors. Second, laboratory-based diagnostic methods, though precise, require specialized equipment and skilled personnel, making them impractical for large-scale or remote applications. Lastly, traditional systems struggle to adapt to the dynamic nature of plant diseases influenced by factors like climate change, pathogen evolution, and shifts in cropping patterns [5][6][7] . To overcome these challenges, the integration of advanced technologies such as Artificial Intelligence (AI) and Machine Learning (ML) has emerged as a game-changer in plant pathology. AI, a branch of computer science that simulates human intelligence, and ML, a subset of AI that focuses on pattern recognition and predictive modelling, offer innovative tools for disease prediction and management. These technologies excel at analysing large and complex datasets, identifying subtle patterns, and generating actionable insights, all in real time [8][9][10][11] .

One of the most transformative applications of AI and ML in agriculture is image-based disease detection. Highresolution images of plant leaves, stems, and fruits are processed using ML algorithms to identify diseases with remarkable accuracy. Deep learning, a powerful subset of ML, leverages Convolutional Neural Networks (CNNs) to recognize patterns in images, distinguishing between healthy and diseased plants with precision often exceeding that of human experts. Such systems not only reduce diagnostic errors but also enable early detection of diseases, allowing for timely intervention and minimizing crop losses. Beyond image analysis, AI models also incorporate environmental data such as temperature, humidity, and rainfall to predict disease outbreaks. For instance, fungal diseases are often associated with specific climatic conditions. By analysing real-time and historical weather data, ML algorithms can provide early warnings, empowering farmers to implement preventive measures. These predictive models are particularly valuable in largescale farming operations, where manual monitoring of disease symptoms is impractical [12][13][14][15] . The advent of IoT (Internet of Things) devices and remote sensing technologies has further enhanced the capabilities of AIdriven systems in agriculture. Sensors deployed in fields and drones equipped with imaging devices collect vast amounts of data, which are then processed by AI algorithms to monitor plant health and detect potential disease outbreaks. These real-time monitoring systems offer a scalable solution for disease management, particularly in regions with vast agricultural landscapes or limited access to human expertise. The benefits of AI and ML in plant disease prediction extend beyond accuracy and speed. These technologies also facilitate cost-effective disease management by reducing the need for extensive field inspections and laboratory tests. Additionally, they enable personalized recommendations tailored to the specific conditions of individual farms, optimizing resource use and minimizing environmental impact. For example, site-specific disease prediction models can guide the targeted application of fungicides, reducing unnecessary chemical usage and promoting sustainable farming practices [16] . Despite their potential, the implementation of AI and ML in plant pathology is not without challenges. High-quality datasets are essential for training accurate models, but the availability of such data is often limited. Furthermore, AI models trained on specific crops or regions may struggle to generalize to new conditions, necessitating continuous model updates and validations. Additionally, the adoption of AI-driven tools requires investments in technology and infrastructure, which may be a barrier for smallholder farmers or those in developing regions. Ethical considerations also play a role in the adoption of AI in agriculture. Ensuring equitable access to these technologies and addressing concerns about data privacy and ownership are critical to fostering trust and widespread adoption. Policymakers and stakeholders must work collaboratively to create an ecosystem that supports innovation while addressing these challenges [17] . AI and ML are poised to revolutionize plant pathology by offering efficient, scalable, and accurate solutions for disease prediction and management. As these technologies continue to evolve, they promise to enhance the resilience of agricultural systems, reduce crop losses, and contribute to global food security. This review explores the latest advancements in AI and ML-driven disease prediction models, emphasizing their potential to transform plant pathology and their role in addressing the challenges of modern agriculture.

Traditional Models

Traditional plant disease prediction models rely on statistical techniques and expert knowledge to forecast the likelihood of disease outbreaks. These models have been instrumental in understanding disease dynamics and offering practical solutions for disease management in agriculture.

Epidemiological Models

Epidemiological models analyse environmental factors such as temperature, humidity, rainfall, and crop phenology to predict the onset and spread of plant diseases. For example, Degree-Day models estimate the accumulation of heat units required for the development of fungal pathogens. Similarly, simulation-based approaches like the Monilinia Risk Assessment System are used to predict fruit rot in orchards [18] . These models provide valuable insights into disease life cycles, enabling farmers to take preventive measures at critical times.

Rule-Based Systems

Rule-based systems apply predefined rules derived from expert knowledge and experimental data to predict disease conditions. These systems often rely on thresholds, such as specific temperature or moisture levels, to generate alerts. For instance, a rule might state that a certain level of humidity combined with warm temperatures indicates a high risk of late blight in potatoes.

Limitations

While these traditional approaches have been effective, they are constrained by their reliance on limited datasets and static algorithms. They struggle with the complexity of realworld agricultural systems, where multiple variables interact in non-linear ways. Furthermore, they are less adaptable to new diseases, evolving pathogen strains, or rapidly changing climatic conditions. As the scale and complexity of agricultural challenges grow, these limitations highlight the need for more sophisticated methods, paving the way for the adoption of Artificial Intelligence (AI) and Machine Learning (ML) models, which offer greater flexibility, scalability, and precision [19] .

Machine Learning Models

Machine Learning (ML) models have transformed plant pathology by enabling data-driven, accurate, and scalable disease prediction systems. These models learn patterns from historical and real-time data to predict disease occurrence, often outperforming traditional models in terms of accuracy and adaptability.

Support Vector Machines (SVMs)

Support Vector Machines are widely used for disease classification tasks due to their effectiveness in handling complex datasets. SVMs classify data points by finding an optimal hyperplane that separates classes [20] . For example, they have been applied to classify plant diseases based on spectral data from leaves or imaging data from infected crops. SVMs are particularly effective for binary or multiclass classification problems and are known for their robustness in small or medium-sized datasets.

Random Forests

Random Forests, a type of ensemble learning method, are highly effective in handling large and diverse datasets. They work by creating multiple decision trees and aggregating their outputs to make predictions. Random Forests are particularly adept at identifying key predictors of diseases, such as environmental variables, pathogen traits, or host susceptibility. Their ability to manage missing data and reduce overfitting makes them a popular choice in plant disease prediction tasks [21] .

K-Nearest Neighbours (KNN)

K-Nearest Neighbours is a simple yet effective algorithm for disease classification, especially in small-scale studies. KNN classifies a new data point based on the majority class of its closest neighbours in the feature space. It has been successfully used in tasks such as identifying disease symptoms in plants from spectral or morphological data. However, KNN is computationally intensive for large datasets and less effective in high-dimensional spaces compared to other ML models.

Advantages of ML Models

These ML techniques excel in extracting insights from large, complex datasets, offering flexibility to adapt to various plant diseases and environmental conditions. Their ability to process real-time data from sensors and images enables dynamic disease monitoring and early intervention. As a result, ML models are increasingly being integrated into agricultural management systems for effective disease prediction and mitigation [22] .

Deep Learning Models

Deep learning models represent a cutting-edge approach to plant disease prediction, offering unprecedented accuracy and adaptability. Unlike traditional ML algorithms, deep learning models automatically learn feature representations from raw data, eliminating the need for manual feature extraction. Their ability to process vast and complex datasets has made them a cornerstone in modern plant pathology.

Convolutional Neural Networks (CNNs)

CNNs are widely regarded as the most effective deep learning model for image-based disease detection and classification. They excel in identifying visual patterns and features in plant images, such as lesions, discolorations, or abnormal growths caused by fungal, bacterial, or viral infections. For instance, CNNs have been trained on large datasets like Plant Village, achieving high accuracy in detecting diseases across multiple crop types. Advanced architectures like ResNet and EfficientNet further enhance performance by enabling deeper network structures while mitigating issues like overfitting [23] .

Recurrent Neural Networks (RNNs)

RNNs are tailored for sequential or time-series data, making them suitable for monitoring disease progression over time. By analyzing data such as daily weather conditions, pest activity, or crop phenology, RNNs can predict the likelihood and severity of disease outbreaks. Long Short-Term Memory (LSTM) networks, a variant of RNNs, are particularly effective in capturing long-term dependencies in time-series data, enabling more accurate disease trend predictions [24] .

Generative Adversarial Networks (GANs)

GANs are innovative tools for data augmentation and synthetic image generation. In plant pathology, GANs are used to generate realistic images of diseased plants, which are valuable for training deep learning models in cases where real-world data is limited. For example, GANs can create synthetic images of rare diseases or simulate various stages of infection, improving model robustness and generalizability [25] .

Advantages of Deep Learning Models

High Accuracy: Deep learning models can achieve diagnostic accuracies comparable to or exceeding human experts.

Scalability: These models can handle large datasets from diverse sources, including satellite imagery, drone footage, and microscopic analyses.

Automation: They enable end-to-end automation, from feature extraction to prediction, reducing reliance on manual intervention.

Challenges

Advantages, deep learning models require substantial computational resources and large datasets for effective training. Additionally, the "black-box" nature of deep learning can make it challenging to interpret results, necessitating further research to enhance explainability., deep learning models are revolutionizing plant disease prediction by integrating advanced computational capabilities with precision agriculture, offering scalable and accurate solutions for disease management [26] .

Applications of AI and ML in Plant Disease Prediction

The integration of Artificial Intelligence (AI) and Machine Learning (ML) in plant pathology has revolutionized how diseases are detected, monitored, and managed. These technologies offer innovative, data-driven solutions that enhance the precision and efficiency of disease prediction, benefiting both small-scale farmers and large agricultural enterprises. Below are the key applications of AI and ML in plant disease prediction.

Image-Based Disease Detection

Image-based disease detection has emerged as one of the most significant applications of AI in plant pathology. Highresolution images of crops are processed using advanced algorithms to identify visual symptoms such as lesions, discoloration, or spots, which may indicate diseases.

Mobile Applications: AI-powered mobile apps enable farmers to diagnose plant diseases by simply capturing images with their smartphones. These apps, equipped with deep learning models like Convolutional Neural Networks (CNNs), provide instant feedback and actionable advice.

Drone Technology: Drones equipped with multispectral or hyperspectral cameras capture large-scale field images. AI algorithms process these images to detect and map disease distribution across fields, facilitating targeted intervention.

Case Study: The Plant Village dataset, which contains thousands of annotated plant disease images, has been instrumental in training models to achieve high diagnostic accuracy across diverse crops and diseases.

Environmental Data Integration

Environmental conditions play a pivotal role in the onset and spread of plant diseases. ML models integrate real-time and historical environmental data, such as temperature, humidity, and rainfall, to predict disease outbreaks with high accuracy.

Disease-Specific Models: For example, late blight in potatoes-a devastating fungal disease-is strongly influenced by specific weather patterns. ML algorithms analyze temperature and humidity trends to predict outbreaks, enabling farmers to take preventive measures.

Data Sources: These predictions leverage diverse datasets, including weather station data, satellite imagery, and IoTbased sensor networks installed in fields. By correlating environmental factors with disease incidence, these models help optimize disease management strategies tailored to specific locations and conditions [27] .

Precision Agriculture

AI and ML are driving the adoption of precision agriculture, a farming approach that tailors interventions to specific areas of a field, minimizing resource wastage and maximizing productivity.

Targeted Pesticide Application: AI-powered systems identify disease hotspots within a field, enabling sitespecific pesticide application rather than blanket spraying. This reduces pesticide use, cuts costs, and minimizes environmental impact.

Yield Optimization: Disease prediction models inform farmers about potential yield losses, allowing them to focus efforts on high-risk areas and maintain optimal crop health. Precision agriculture technologies are also integrated with autonomous systems, such as robotic sprayers and drones, to execute interventions seamlessly [28] .

Early Warning Systems

AI-driven predictive models are essential for developing real-time early warning systems that alert farmers to potential disease outbreaks.

Real-Time Alerts: By combining disease prediction algorithms with IoT sensors, farmers receive timely alerts about conditions conducive to disease development.

Example: In rice farming, models predict bacterial leaf blight based on environmental conditions and crop phenology, giving farmers time to implement protective measures.

Scalable Solutions: These systems are scalable, benefiting both individual farmers and large-scale agribusinesses through regional disease forecasts. Early warning systems reduce crop losses by ensuring timely interventions, such as fungicide application or quarantine measures, to contain disease spread [29] . The continued advancement of AI and ML technologies promises to enhance the efficiency of plant disease prediction further. Future applications may include integration with blockchain for data transparency, real-time pathogen genome analysis, and the use of edge computing to process data directly in the field. As these technologies evolve, they will play a critical role in ensuring food security and sustainable agricultural practices worldwide, the application of AI and ML in plant disease prediction addresses critical challenges in modern agriculture by enabling accurate, real-time, and actionable solutions. From image-based diagnostics to early warning systems, these technologies empower farmers with the tools to protect crops, reduce losses, and optimize resource use, ensuring long-term agricultural sustainability [30][31] .

Challenges in AI and ML for Plant Pathology

The transformative potential of AI and Machine Learning (ML) in plant pathology, several challenges hinder their effective implementation and widespread adoption. Addressing these issues is critical to ensure that these technologies are accessible, scalable, and beneficial across diverse agricultural contexts [32] . One significant challenge is the quality and availability of data. ML models rely heavily on high-quality, labeled datasets for training and validation. However, such datasets are often scarce, incomplete, or region-specific. Labeling plant disease data requires expert knowledge, which is both time-consuming and expensive. Furthermore, environmental variations such as seasonal changes and regional differences in climate make it difficult to create datasets that are universally applicable. This lack of standardized, high-quality data limits the accuracy and generalizability of AI models across different crops and geographies. Scalability is another critical issue. Many AI models are designed for specific crops or diseases, making them less effective when applied to other contexts. For instance, a model trained on wheat diseases in a temperate region may not perform well in identifying diseases in rice cultivated in tropical climates. Variability in soil types, farming practices, and weather conditions across regions further complicates the scalability of these technologies. Adapting models to local conditions requires significant resources, which may not always be feasible [33] . Integrating AI tools into farming practices presents additional challenges. Many existing systems lack user-friendly interfaces, making them difficult for farmers, particularly those with limited technical expertise, to adopt. Moreover, effective deployment of these tools requires training programs to familiarize farmers with the technology and its potential benefits. Without such support, farmers may struggle to incorporate AI-driven solutions into their routine practices, reducing the overall impact of these innovations. Ethical and economic concerns also pose barriers to the adoption of AI and ML in plant pathology. The high cost of AI-powered tools and devices can exclude small-scale farmers, who constitute a significant proportion of the global farming community. Additionally, unequal access to these technologies may exacerbate existing disparities between large agribusinesses and individual farmers. Ethical considerations, such as data ownership and the fair distribution of AI benefits, must also be addressed to ensure equitable access and prevent the monopolization of AIdriven agricultural solutions, while AI and ML hold immense promise for revolutionizing plant pathology, challenges related to data quality, scalability, integration with farming practices, and ethical concerns must be tackled. Collaborative efforts involving researchers, policymakers, technology developers, and farmers are essential to overcome these hurdles and realize the full potential of. As AI and Machine Learning continue to evolve in the field of plant pathology, there are several key areas where future research and development can help maximize their potential for agricultural advancement. By addressing existing challenges and building on current technologies, the next phase of AI integration in plant disease management can bring even greater benefits to global food security and sustainable agriculture.

Improved Data Collection

The success of AI and ML models in plant pathology heavily depends on the quality and scale of data available for training. As such, the future of plant disease prediction will involve leveraging advanced data collection technologies like the Internet of Things (IoT) devices and satellite imagery. IoT devices, such as soil sensors, weather stations, and crop monitoring drones, can collect real-time environmental and crop health data at large scales. This would allow AI models to be more dynamic and responsive to the changing conditions of farms. Satellite imagery, on the other hand, can be used to monitor crop health over large geographic areas, providing valuable insights into disease progression and environmental stressors that could influence plant diseases. With improved, large-scale data collection, AI systems can better predict and prevent disease outbreaks before they become widespread.

Model Explainability

One of the critical barriers to the widespread adoption of AI in agriculture is the opacity of many machine learning models, particularly deep learning models. While these models can achieve high accuracy in predicting plant diseases, their "black-box" nature makes it difficult for farmers and stakeholders to understand how decisions are made. Future research should focus on enhancing the explainability of AI models, making them more transparent and interpretable. This would not only build trust with farmers but also help them make informed decisions about disease management and prevention. If farmers understand why a particular disease prediction was made, they will be more likely to trust and adopt AI-driven systems in their daily farming practices.

Multi-Crop Models

As agriculture is diverse, with different crops being grown in varying climatic and geographical conditions, one of the challenges faced by AI models is their ability to generalize across multiple crops and diseases. To address this, future research should focus on developing robust AI and ML models that can work across a range of crops and environmental conditions. These models should be flexible enough to handle multiple disease scenarios and various pathogens, ensuring their applicability to diverse farming practices. Multi-crop models would be particularly beneficial in regions where small-scale farmers grow a wide variety of crops, providing them with a single tool to predict and manage diseases across different crops, ultimately leading to better resource utilization and increased yield.

Integration with Policy

To fully harness the power of AI in plant disease prediction, it is essential to integrate these technologies into broader agricultural policy frameworks. Policymakers should collaborate with AI researchers and practitioners to ensure that AI tools are aligned with sustainable agricultural practices and accessible to all farmers, especially smallscale and resource-poor farmers. Policy interventions could involve funding research in AI-based plant health monitoring, ensuring equitable access to AI tools, and incentivizing the adoption of AI technologies by farmers. Additionally, policies could promote the use of AI-driven insights to guide agricultural practices, such as optimizing pesticide use or preventing the spread of disease through targeted interventions. By aligning AI innovations with policy efforts, governments can encourage sustainable, datadriven decision-making that benefits farmers, consumers, and the environment alike [34-35], the future of AI and ML in plant pathology is promising, with opportunities to revolutionize disease detection and management. Through improved data collection, increased model explainability, the development of multi-crop solutions, and integration with policy, the potential for AI-driven plant disease prediction can be fully realized, ensuring that farmers are equipped with the tools necessary to face the growing challenges of global food security.

Conclusion

AI and ML are significantly transforming the field of plant disease prediction, bringing new possibilities for early detection and intervention that were previously unimaginable. These advanced technologies allow for accurate and timely identification of plant diseases, enabling farmers to take preventive measures before diseases spread widely, reducing crop losses, and ensuring better yield and food security. By leveraging vast datasets, such as images, environmental factors, and historical disease patterns, AIdriven systems are helping researchers and farmers detect even the most subtle signs of disease, improving both the speed and precision of disease management. Despite the promising advancements, there remain several challenges to overcome, including the need for high-quality data, scalability of models across different regions and crops, and the integration of these tools into everyday farming practices. Future research will need to focus on improving data collection through the use of IoT devices and satellite imagery, enhancing model explainability to ensure farmer trust, and developing multi-crop models that can cater to diverse agricultural landscapes. The successful implementation of AI and ML in plant pathology will not only improve disease management but also contribute to more sustainable agricultural practices. By collaborating across disciplines-combining the expertise of researchers, technologists, and policymakers-AI-driven plant disease prediction can play a pivotal role in tackling the challenges of global food security. Ultimately, these innovations will empower farmers, increase crop productivity, and help ensure that agriculture remains resilient in the face of a changing climate and growing global population.

References

1. Bhange M, Hingoliwala H. Smart farming: Pomegranate disease detection using image processing. Procedia Computer Science. 2015;58:280-288.
2. Kamilaris A, Prenafeta-Boldú FX. Deep learning in agriculture: A survey. Computers and Electronics in Agriculture. 2018;147:70-90.
3. Mohanty SP, Hughes DP, Salathé M. Using deep learning for image-based plant disease detection. Frontiers in Plant Science. 2016;7:1419.
4. Zhang S, Huang W, Zhang C. Three-channel convolutional neural networks for vegetable leaf disease recognition. Cognitive Systems Research. 2019;53:31-41.
5. Akdemir D, Meles B. A review of machine learning techniques for plant disease classification. Computers and Electronics in Agriculture. 2021;188:106287. https://doi.org/10.1016/j.compag.2021.106287
6. Amiri B, Khosla R. AI-driven precision agriculture: A review of applications and future directions. Environmental Science & Technology. 2020;54(6):3170-3181. https://doi.org/10.1021/acs.est.9b05617
7. Bendre A, Suri HS. Detection of plant diseases using deep learning: A review. Journal of Plant Pathology. 2020;102(2):437-449. https://doi.org/10.1007/s42161019-00452-z
8. Chen Y, Li Y, Zhang Y. Convolutional neural networks for plant disease recognition: A survey. Computers, Materials & Continua. 2021;66(3):2677-2692. https://doi.org/10.32604/cmc.2021.016251
9. Ghosal S, Pati S. Applications of machine learning techniques in agriculture: A review. Computational Intelligence and Neuroscience. 2022;2022:1234810. https://doi.org/10.1155/2022/1234810
10. Raia Firdous, Nazneen S. Comparative Analysis of Calcium Oxalate Accumulation in Indian Vegetables and Napier Grass Versus Spinach. Environmental Reports: an International Journal. 2019;1(1):10-16. https://doi.org/10.51470/ER.2019.1.1.10
11. He J, Liu Y. Deep learning for plant disease detection: A survey. Computers and Electronics in Agriculture. 2019;162:365-373. https://doi.org/10.1016/j.compag.2019.04.031
12. Hough S, Fox R. Artificial intelligence in agriculture: A framework for plant disease management. Agricultural Systems. 2020;179:102736. https://doi.org/10.1016/j.agsy.2019.102736
13. VijayKumar R. Biochar in Soil Restoration: A Comprehensive Review on Enhancing Soil Health and Carbon Sequestration. Environmental Reports: an International Journal. 2019;1(1):5-9. https://doi.org/10.51470/ER.2019.1.1.05
14. Kaur P, Singh J. A survey on plant disease detection and prediction using machine learning techniques. Artificial Intelligence in Agriculture. 2020;4:11-22. https://doi.org/10.1016/j.aiia.2020.02.001
15. Li X, Zhang Y. Machine learning techniques in plant disease prediction: A comprehensive review. Biosystems Engineering. 2020;195:150-168. https://doi.org/10.1016/j.biosystemseng.2020.06.002
16. Ramesh S. The Role of Nature-Based Solutions in Climate Change Adaptation and Mitigation. Environmental Reports: an International Journal. 2019;1(1):1-4. https://doi.org/10.51470/ER.2019.1.1.01
17. Liu X, Zhang Y. Using deep learning for plant disease detection: A comprehensive review. Pattern Recognition Letters. 2021;137:144-151. https://doi.org/10.1016/j.patrec.2020.11.006
18. VijayKumar R. Integrating Indigenous Knowledge and Traditional Practices for Biodiversity Conservation in a Modern World. Environmental Reports: an International Journal. 2019;1(2):4-7. https://doi.org/10.51470/ER.2019.1.2.04
19. Mohanty SP, Hughes DP, Salathé M. Using deep learning for image-based plant disease detection. Frontiers in Plant Science. 2016;7:1419. https://doi.org/10.3389/fpls.2016.01419
20. Saransh Kumar Gautam. The Role of Indigenous Knowledge in Biodiversity Conservation: Integrating Traditional Practices with Modern Environmental Approaches. Environmental Reports: an International Journal. 2019;1(2):1-3. https://doi.org/10.51470/ER.2019.1.2.01
21. Ahmed Z, Ellahi T, Muthukumaran M, Vidhya CS, Belagalla N. Enhanced Pollutant Removal and Power Generation in Wastewater Using Microbial Fuel Cells: A Pathway to Sustainable Energy. Environmental Reports: an International Journal. 2024;6(1):30-34. https://doi.org/10.51470/ER.2024.6.1.30
22. Eyenghe Tari, Brown Ibama, Le-ol Anthony, Evangeline Nkiruka. Physical Planning as a Tool to Address Declining Urban Residential Quality and Quality of Life in Select Neighbourhoods in Yenagoa City. Environmental Reports: an International Journal. 2024;6(1):23-29. https://doi.org/10.51470/ER.2024.6.1.23
23. Niamir A, Berthold M. Application of machine learning techniques for plant disease classification: A review. Biosystems Engineering. 2020;189:155-168. https://doi.org/10.1016/j.biosystemseng.2019.10.015
24. Pandey S, Choi JH. Applications of machine learning in plant disease detection: A review. Precision Agriculture. 2021;22(5):1199-1218. https://doi.org/10.1007/s11119-020-09739-1
25. Ogboeli Goodluck Prince, Brown Ibama. Planning Implications of the Effect of Crude Oil Pollution on Germination and Growth Parameters of Mucuna Pruriens (Var. Cochinchinesis) Fabaceain Aluu Town, Rivers State, Nigeria. Environmental Reports: an International Journal. 2024;6(1):15-22. https://doi.org/10.51470/ER.2024.6.1.15
26. Salehahmadi Z, Kiani H. Artificial intelligence applications for plant disease detection: A review. Computers and Electronics in Agriculture. 2020;175:105589. https://doi.org/10.1016/j.compag.2020.105589
27. Safdar EA, Safdar NA, Khan PA. A Survey to Assess Knowledge Attitude Practice of People towards Vitamin D. Acta Traditional Medicine. 2023;2(1):2734.
28. Athokpam V, Chamroy T, Ngairangbam H. The Role of Urban Green Spaces in Mitigating Climate Change: An Integrative Review of Ecological, Social, and Health Benefits. Environmental Reports: an International Journal. 2024;6(1):10-14. https://doi.org/10.51470/ER.2024.6.1.10
29. Wang X, Zhang H. Deep learning for plant disease detection and diagnosis: A review. Computers in Industry. 2019;108:179-190. https://doi.org/10.1016/j.compind.2019.01.014
30. Krishnaveni B, Shailaja K, Chapla J. Water Quality Assessment of Bibinagar Lake by Physico-Chemical Parameters. Environmental Reports: an International Journal. 2024;6(1):1-9. https://doi.org/10.51470/ER.2024.6.1.01
31. Voruganti C. Biochar Applications in Soil Restoration: Enhancing Soil Health and Carbon Sequestration. Environmental Reports: an International Journal. 2023;5(1):1-4. https://doi.org/10.51470/ER.2023.5.1.01
32. Safdar EA, Tabassum R, Khan PA, Safdar NA. Cross sectional retrospective study on mifepristone and misoprostol combination vs misoprostol alone for induction of labour in management of IUFD. Acta Pharma Reports. 2023;2:1-4.
33. Safdar EA, Noor S, Safdar NA. A Survey To Assess Knowledge Attitude Practice Of Participants Towards Antibiotics Use and Resistance. Indo-American Journal of Pharma and Bio Sciences. 2023;21(4):1-24.
34. Safdar NA, Ghori SS, Fatima SJ, Humera S, Rafia K. Formulation and in vitro evaluation of zolpidem tartrate sub-lingual tablet. Biochemical and Cellular Archives. 2023;23(2):[Page numbers if available].
35. Safdar NA, Nikhat EAS, Fatima SJ. Cross-sectional study to assess the knowledge, attitude, and behavior of women suffering from PCOS and their skin. Acta Traditional Medicine. 2023;V2(1):19-26.