Quantifying Mango (Mangifera Indica) Leaf Diseases Considering the Level of Elevation Using Convolutional Neural Networks (CNNs)

Mango leaf diseases pose a significant problem for global agriculture, including the Philippines, where mango production contributes substantially to the Gross Domestic Product (GDP). This research quantifies leaf disease prevalence, determines the proportion of healthy leaves, and identifies specific diseases using Convolutional Neural Networks (CNNs), which offer image analysis accuracy exceeding 90%. A stratified sampling method a method of sampling that involves the division of a population into smaller sub-groups known as strata, was utilized using elevation as the stratification factor, was employed to ensure data reliability while minimizing the number of barangays surveyed Photographs taken in representative areas of each elevation stratum were processed using a web application to collect data Gall midge infestation was dominant at low and medium elevations, while dieback was prevalent at high, very high, and extremely high elevations. However, gall midge remained the most prevalent disease across the entire municipality, while anthracnose was the least prevalent, with an incidence rate of 0.5. This study revealed that 125 out of 200 analysed leaves exhibited disease, leaving 75 out of 200 healthy. This research also demonstrates the efficacy of Convolutional Neural Networks (CNN) in identifying mango leaf diseases. Overall, the data gathered demonstrates that lower elevations show a higher incidence of leaf diseases, while higher elevations exhibit lower rates.

Leaf diseases, Mango, Convolutional Neural Networks, Web-based application. Elevation

1. Agrawal, S., & Saklani, P. (2023). Physiological responses of the leaves of a high-altitude plant Picrorhiza kurroa to cold stress. Plant Science Today. https://doi.org/10.14719/pst.2861 [Google Scholar] [Crossref]

2. Alberto, R. (2020). Development of integrated disease management program against Anthracnose-Twister (Colletotrichum gloeosporioides-Gibberella moniliformis) disease of onion (Allium cepa). Plant Pathology & Quarantine, 10(1), 111–119. https://doi.org/10.5943/ppq/10/1/13 [Google Scholar] [Crossref]

3. Belachew, K., Senbeta, G. A., Garedew, W., Barreto, R. W., & Del Ponte, E. M. (2020). Altitude is the main driver of coffee leaf rust epidemics: a large-scale survey in Ethiopia. Tropical Plant Pathology, 45(5), 511–521. https://doi.org/10.1007/s40858-020-00383-4 [Google Scholar] [Crossref]

4. Blanche, K. R., & Ludwig, J. A. (2001). Species Richness of Gall-inducing Insects and Host Plants along an Altitudinal Gradient in Big Bend National Park, Texas. The American Midland Naturalist, 145(2), 219–232. https://doi.org/10.1674/0003-0031(2001)145 [Google Scholar] [Crossref]

5. C, M., Kumar, L. V., Navi, S., G, S., & Sanathkumar, V. (2020). Survey on the incidence of Asian rice gall midge, Orseolia oryzae (Cecidomyiidae: Diptera) in Cauvery command area. International Journal of Chemical Studies, 8(6), 1731–1735. https://doi.org/10.22271/chemi.2020.v8.i6y.11015 [Google Scholar] [Crossref]

6. Gangaraju, P., Hegde, M., Mallapur, C., & Ka, A. (2020). New report of branch gall midge (Procontarinia Sp.) on mango in Karnataka. Journal of Entomology and Zoology Studies, 8(5), 184–186. http://www.entomoljournal.com/archives/2020/vol8issue5/PartC/8-4-141-433.pdf [Google Scholar] [Crossref]

7. Kaur, L., & Sharma, S. G. (2021). Identification of plant diseases and distinct approaches for their management. Bulletin of the National Research Centre/Bulletin of the National Research Center, 45(1). [Google Scholar] [Crossref]

8. Kulkarni, S. B., & Keerthi, J. (2023). Mango leaf disease detection using deep learning. International Journal for Research in Applied Science and Engineering Technology, 11(8), 1203–1208. https://doi.org/10.22214/ijraset.2023.55325 [Google Scholar] [Crossref]

9. Liebig, T., Ribeyre, F., Läderach, P., Poehling, H., Van Asten, P., & Avelino, J. (2019). Interactive effects of altitude, microclimate and shading system on coffee leaf rust. Journal of Plant Interactions, 14(1), 407–415. https://doi.org/10.1080/17429145.2019.1643934 [Google Scholar] [Crossref]

10. Mohammed Ezzeldean. (2024, September 24). Mango Leaf Diseases Classification|EfficientnetB0. Kaggle. https://www.kaggle.com/code/mohammedezzeldean/mango-leaf-diseases-classification-efficientnetb0/input [Google Scholar] [Crossref]

11. Mustafa, G., Imran, M., Nadeem, S., Ahmad, M., IQBAL, A., Ali, I., Hasnain, M., MANN, N., HUSSAIN, R., AKRAM, M., & Hamza, M. A. (2024). Management of major pre and postharvest fungal disease (anthracnose) of mango fruits – a review. Biological & Clinical Sciences Research Journal, 2024(1), 1317. https://doi.org/10.54112/bcsrj.v2024i1.1317 [Google Scholar] [Crossref]

12. Wubshet, T., Wang, Z., Yang, J., Chen, H., Schaefer, D., Goldberg, S., Mortimer, P., Lu, P., & Xu, J. (2021). Effect of elevation on photosynthesis of young mango (Mangifera indica L.) trees. Photosynthetica, 59(4), 508–516. https://doi.org/10.32615/ps.2021.040 [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet