Crop Prediction on Indian Agriculture.pptx

This ppt has the topic of Indian Agriculture named Crop Prediction on Indian Agriculture using different machine learning algorithms.

1. Noida Institute of Engineering & Technology Department of CSE (DS) Session (2023-24) Capstone Project (ACSE0859) Presentation on “CROP PREDICTION ON INDIAN AGRICULTURE USING MACHINE LEARNING” Project Guide: Submitted To: Group Members: Mrs. Nisha Dr. Raju Sudhanshu Pal (2101331549014) Asst. Prof. CSE(DS) Vibhav Gupta (2101331549015) Nityanand Singh (2101331549010)

2. Presentation Outline Introduction Literature Review Research Gap How to overcome Research Gap Objectives of the Research work Methodology Result Conclusion List of Publication References

3. Introduction The agricultural landscape of India stands on the cusp of transformation, fueled by technological advancements and data-driven insights. In this pursuit, our research endeavors to bridge the gap between traditional farming practices and modern predictive analytics, ushering in a new era of precision agriculture. At the heart of our project lies a comprehensive analysis of historical data on crop yields, weather patterns, and various influencing factors meticulously curated from the Indian Government Repository. With over 2.5 lakh observations spanning attributes such as State, District, Crop, Season, Year, Area, and Production, our model seeks to revolutionize crop prediction for over a hundred crops cultivated across the nation.

4. Literature Review S. No. Author Technology Used Result Limitation 1. Patil, S. M., & Chaudhari, D. S (2017) [1] Machine Learning Techniques, Random Forest, Decision Tree provided a review of existing research in this field. External factors such as natural disasters were not included 2. Gautam, A., Singh, M., & Sharma, V (2018) [2] Random Forest, Support Vector Machine(SVM), Support Vector Regression Improved yield prediction accuracy Limited to specific regions and crop types 3. Das, S., & Bandyopadhyay y, S (2017) [3] Data Mining Techniques, Data Cleaning, Clustering Overview of data mining methods for crop prediction Lack of real-time data, accuracy issues 4. Rao, B. B., & Rao, K. S (2018) [4] Machine Learning Algorithms, Random Forest, KNN Improved prediction accuracy compared to traditional methods Data availability and quality 5. Bhowmick, S., Ghosh, D., & Dash, S (2018) [5] Artificial Neural Networks, Decision Trees Accurate yield predictions for specific crops Limited to specific crop type, weather conditions 6. Kumar, A., & Goyal, M (2019) [6] Linear Regression, K- Means Clustering Improved yield forecasting using clustering techniques Data quality, variability in farming practices

5. Research Gap While existing literature provides valuable insights into crop prediction using machine learning in Indian agriculture, several gaps persist, necessitating further investigation: Limited Regional Specificity Data Quality and Availability Model Interpretability and Scalability Dynamic Environmental Factors Crop Disease Prediction Addressing these research gaps is paramount for advancing the field of crop prediction in Indian agriculture, empowering farmers with actionable insights and fostering sustainable agricultural practices.

6. Objective of the Research work T he primary objective of this research is to develop a robust machine learning model for accurate crop prediction in Indian agriculture. The specific aims include: Implement advanced regression techniques and ensemble methods to improve the precision of crop yield forecasts, leveraging historical data on crop yields, weather patterns, and relevant agricultural factors. Empower farmers with actionable insights by providing predictions for over a hundred crops cultivated across diverse geographical regions in India. Enable informed decisions regarding crop selection, planting schedules, and irrigation practices. Bridge existing gaps in literature by customizing predictive models for regional specificity, enhancing data quality and availability, improving model interpretability, and integrating dynamic environmental factors for real-time predictions. Foster sustainable agricultural practices by optimizing resource allocation, reducing risks associated with crop failure, and promoting crop diversification. Mitigate the impact of climate variability on agricultural productivity through timely and accurate predictions. Develop user-friendly interfaces and educational resources to facilitate widespread adoption of predictive analytics among farmers, extension workers, and agricultural policymakers. Empower stakeholders with the knowledge and tools to navigate modern agricultural challenges effectively.

7. Methodology The primary objective of this research is to develop a robust machine learning model for accurate crop prediction in Indian agriculture. The specific aims include: Data Collection and Preprocessing: Utilized a publicly available dataset comprising factors influencing crop yield, including temperature, humidity, soil moisture, and crop type. Cleaned data by replacing missing values and performed feature engineering to create new relevant features. Exploratory Data Analysis (EDA): Generated statistical summaries, correlation matrices, and heatmaps to understand data distribution and relationships between features. Visualized climatic trends over time using bar charts. Model Selection and Training: Experimented with various regression techniques including Linear Regression, Decision Tree Regression, Random Forest Regression, and Support Vector Regression (SVR) to capture complex patterns in the data. Model Evaluation: Assessed models' predictive accuracy using metrics such as Mean Squared Error (MSE), R-squared (R2) Score, and cross-validation techniques to ensure robustness and reliability.

8. Methodology 1 Performance Measurement of Decision Tree 2 Performance Measurement of Random Forest 1.1 Performance Measurement of Decision Tree 3 Performance Measurement of Decision Tree

9. Result Achieved high accuracy in crop yield predictions across diverse geographical regions and crop types. Models demonstrated robust performance, capturing complex relationships between environmental factors and crop production. Identified Random Forest Regression as the most effective model for crop yield prediction, outperforming other regression techniques. Ensemble methods and feature scaling techniques significantly enhanced prediction accuracy. Validated model predictions against ground truth data, confirming reliability and applicability in real-world agricultural settings. Farmers can confidently utilize predictions for informed decision-making regarding crop selection, planting schedules, and resource allocation. Continued research to enhance model performance through integration of real-time data and advanced machine learning techniques. Collaboration with agricultural stakeholders to facilitate widespread adoption and implementation of predictive analytics in farming communities.

10. Result 4 Accuracy of Random Forest, Decision Tree and SVR Model

11. Conclusion In conclusion, our research represents a significant advancement in the domain of crop prediction in Indian agriculture using machine learning techniques. Through meticulous data collection, preprocessing, and model selection, we have successfully developed a robust predictive model capable of accurately forecasting crop yields across diverse geographical regions and crop types.

12. List of Publication INTERNATIONAL JOURNAL OF RESEARCH AND ANALYTICAL REVIEWS (IJRAR) has accepted our paper “ Advancing Crop Prediction in Indian Agriculture: A Data Driven Approach

13. References We uses many references for this Project, some of them is given below: [1]. Patil (S.M.), Chaudhari (D.S.), et al. (2017), Review of Crop Yield Prediction Using Machine Learning Techniques, International Conference on trends in electronics and informatics (ICEI), pp. 245 to 249. [2]. Gautam, A., Singh,M., & Sharma,V. (2018) Crop yield prediction with the help of machine learning algorithms. ICCCNT 9th Annual Conference, pp. 1-6. [3]. Das (S), S. & Bhatnagar (S) (2017) Survey on Crop Yield Prediction using Data Mining Techniques. ICCES 2nd Annual Conference, pp. 1321 to 1326. [4]. Rao, B.B., and Rao, K.S. , Crop yield prediction with the help of machine learning algorithms, 2018 4th International CATccT, pp. 69-72. [5]. Bhowmick (S), Ghosh (D), & Dash (S) (2018), Crop yield prediction with the help of machine learning algorithms. Calcutta Conference, 2018, pp. 128-133. [6]. Kumar (A), & Goyal (M), 2019. Machine Learning for Crop Yield Prediction. ICECCOT 2019, pp. 1-6. [7]. Agarwal (A), & Somani (A) (2020). Machine Learning for Crop Yield Prediction. ICOSEC 2020, pp. 574 to 578. [8]. Jadhav (S), Sonawane (P), 2020 . Machine Learning for Crop Yield Prediction by Machine Learning Algorithms. ICSTM 2020 pp 235-239. [9]. Jha (C), K.C., Verma (S) (2021) Crop yield predictions with the help of machine learning: a review. ICACCS 2021 - IEEE 7th Annual Conference (pp. 1243 - 1248).

14. References [10]. Sharma, S., Bansal, P., 2017 Crop yield prediction with the help of machine learning algorithms: a review.2nd International Conference on recent trends in electronics, information & communication technology (RTEICT), pp.2364-2368. [11]. dhakate,A., & thakur,S. (2019) Crop yield prediction by machine learning techniques. 6th International conference on Signal Processing and integrated Networks (SPIN), pp. 161-166. [12]. 12. Kumar P. & Suresh N. (2020) Crop yield prediction with the help of machine learning algorithms. RTEICT 2020 Annual Conference, pp. 949- [13]. S. Subburathy, S. & K. Thangavel (2018) Machine Learning for Crop Yield Prediction. ICSSIT 2018, pp. 8 to 13   [ 14]. Kumar, A., &Patil, P. , Crop yield prediction with the help of machine learning techniques: a review. COMITCon 2019, pp 765-770. [15]. Sivasankar (R), Kumaravel (N) (2018) Crop yield predictions with the help of machine learning algorithms, ICCCI 2018 pp. 1 to 6. [16]. Sharma, P., and Goyal, A., (2019) Machine Learning for Crop Yield Prediction: A Review. ICACCS 5th Annual Conference, pp 493-497. [17]. Subramaniyam (A.), & Perumal (K. 2021) Crop yield prediction with the help of machine learning techniques. 6th ICES 2021, pp. 848- 852.

15. Noida institute of Engineering & Technology Thank you