Publisher

IDUIDU

Journal MUNISI: Military Mathematics and Natural SciencesMUNISI: Military Mathematics and Natural Sciences Abstract

Data mining is part of the Knowledge Discovery in Database (KDD) process. The use of data mining serves to classify, predict, and extract other useful information from large data sets. This study aimed to classify rice plants under treatment (drought stress and control) using data mining, focusing on the analysis of the variables of Leaf Area (LA), Root Length (RL), and Shoot Length (SL). Each classification algorithm has different characteristics, resulting in varied performance results. After testing both classification algorithms, the accuracy results were 71.70% for Naïve Bayes and 73.85% for SVM. This shows that the SVM algorithm performs better than Naïve Bayes algorithms to determine best treatment of rice to support national food security further. Furthermore, It also can be concluded that using a machine learning approach can solve problems in the classification of rice plants affected by drought threats is fairly effective with the maximum score obtained is only 73.85%.

Conclusion

The study concludes that the machine learning approach is effective for selecting the appropriate treatment for rice plants.The Support Vector Machine (SVM) algorithm demonstrated the highest performance with an accuracy of 73.SVMs higher recall indicates a stronger ability to identify drought-affected plants, which is valuable for early drought detection.The developed workflow can be applied to various datasets, making it a significant contribution to future research.

Future Research

Further research should investigate the integration of remote sensing data with these machine learning models to create a real-time drought monitoring system for rice fields, enabling proactive irrigation management. Additionally, exploring the use of deep learning techniques, such as convolutional neural networks, could potentially improve classification accuracy by automatically extracting relevant features from plant images. Finally, studies should focus on incorporating additional physiological and environmental variables, like soil moisture and temperature, into the models to enhance their predictive power and provide a more holistic assessment of rice plant health under drought conditions, ultimately contributing to more resilient and sustainable agricultural practices.

References

1. Managing Land Carrying Capacity: Key to Achieving Sustainable Production Systems for Food Security. managing... mdpi.com/2073-445X/11/4/484Managing Land Carrying Capacity Key to Achieving Sustainable Production Systems for Food Security managing mdpi 2073 445X 11 4 484
2. Water stress resilient cereal crops: Lessons from wild relatives - Toulotte - 2022 - Journal of Integrative... onlinelibrary.wiley.com/doi/10.1111/jipb.13222Water stress resilient cereal crops Lessons from wild relatives Toulotte 2022 Journal of Integrative onlinelibrary wiley doi 10 1111 jipb 13222
3. Rice Cultivation of Superior Variety in Swamps to Increase Food Security in Indonesia. rice cultivation... jstage.jst.go.jp/article/ras/8/0/8_300/_articleRice Cultivation of Superior Variety in Swamps to Increase Food Security in Indonesia rice cultivation jstage jst go jp article ras 8 0 8 300 article
4. View of Performance Analysis of ANN and Naive Bayes Classification Algorithm for Data Classification.... ijisae.org/IJISAE/article/view/934/585View of Performance Analysis of ANN and Naive Bayes Classification Algorithm for Data Classification ijisae IJISAE article view 934 585
5. Machine Learning for Plant Stress Modeling: A Perspective towards Hormesis Management | MDPI. machine... doi.org/10.3390/plants11070970Machine Learning for Plant Stress Modeling A Perspective towards Hormesis Management MDPI machine doi 10 3390 plants11070970

Metadata

File size	577.87 KB
Pages	12
DMCA	Report