Transparent Peer Review By Scholar9
Weather Prediction Using Logistic Regression
Abstract
Prediction of ‘Weather or atmospheric condition’ by AI, machine learning techniques is a process of great challenge. Attempts had been made by Computer, Data-Scientists since long, how this condition can be performed successfully .The objective is to predict weather for a place for certain days, here ‘ALIPORE (42807)’.We collected ‘ALIPORE surface data’ (CSV file) for the period, 1969-2023. After collecting this big data, completed process of ‘data mining’ and necessary ‘feature engineering’ steps along with choosing responsible dependent or independent parameters called as predictors to find results or outputs by various machine learning packages of Python like ‘Pandas’, ‘SEABORN’, ‘STATS MODEL’ etc. ,under ‘SCIKIT LEARN’ as well as various ML code and techniques like 'Shape’, ‘drop null values’, ‘Describe’, ‘Label-encoding’, ‘IV-method’, ‘VIF method’ etc. ,some based on statistical theories . Ultimately equation of ‘Logistic Regression’ had been built with test-train split formula to predict future weather as ‘SIGNIFICANT’ or ‘CLEAR’ for certain test array. During analysis, all the weather phenomena as obtained from this big data set, were classified into two categories. No(1)--- ‘Lightning (code 0)’, ‘Drizzle (Code 5)’, ‘Rain (Code 6)’ and ‘Thunderstorm with rain (Code 9)’---for occurrence of any of these weather phenomena ,data were considered as ‘1’ or ‘SIGNIFICANT’ weather and No (2)---On the other hand , all weather except weather as mentioned above ,No (1),were considered as ‘0’ or ‘CLEAR’ weather.
Murali Mohana Krishna Dandu Reviewer
16 Sep 2024 03:06 PM
Approved
Relevance and Originality
The research article addresses a crucial issue—weather prediction using AI and machine learning. Accurate weather forecasting is vital for sectors such as agriculture and emergency planning, making this study timely and important. The work's originality stems from applying machine learning to a large dataset from 1969 to 2023 for ALIPORE. Although the techniques used are established, focusing on this extensive historical dataset and regional specificity may offer new insights or enhancements in prediction accuracy.
Methodology
The research article presents a robust methodology for weather prediction by utilizing a large dataset and employing data mining and feature engineering. Using Python packages like Pandas, SEABORN, and SCIKIT LEARN, and applying Logistic Regression for binary classification, reflects a solid analytical approach. However, further justification for choosing Logistic Regression and a comparison with other models would clarify the methodology's effectiveness and appropriateness.
Validity & Reliability
The article indicates a strong approach to ensuring data validity and reliability, such as handling missing values and encoding variables. However, the abstract lacks details on evaluating the logistic regression model's performance, which is essential for assessing reliability. Information on evaluation metrics like accuracy and precision, along with the generalizability of findings beyond ALIPORE, would enhance the understanding of the results’ reliability.
Clarity and Structure
The article's clarity could be improved with more detailed explanations of methods and terms like ‘IV-method’ and ‘VIF method’. Although the structure appears logical—starting with data collection and progressing through processing and modeling—the abstract does not detail the presentation and discussion of results. Improved clarity in these areas would help in understanding the study's full scope and findings.
Result Analysis
The result analysis focuses on classifying weather into ‘SIGNIFICANT’ and ‘CLEAR’ categories. However, the abstract lacks detailed information on the logistic regression model's performance and classification accuracy. A more thorough analysis of the model's results, including statistical metrics and practical implications, would provide better insight into its effectiveness and real-world application potential.
4o mini
IJ Publication Publisher
Done Sir
Murali Mohana Krishna Dandu Reviewer