Weather Prediction and Climate Analysis using Machine Learning Algorithms: A Review

Weather Prediction and Climate Analysis using Machine Learning Algorithms: A Review

Dwipen Das

Department of Computer Science and Engineering, Girijananda Chowdhury University

Guwahati, Assam, India

Th. Shanta Kumar

Department of Computer Science and Engineering, Girijananda Chowdhury University

Guwahati, Assam, India

Abstract – Weather prediction and forecasting are very important and it has big impact on the national as well as global economy. Different sectors e.g. agriculture, transportation, tourism, industry etc. are directly depends on weather conditions for operations and production. So, these sectors are affected by weather conditions. Forecasting is playing a crucial role in decision making for severe weather condition and management. The nature of the weather is erratic, uncertain and very complex which makes the traditional weather forecasting system a tedious and challenging task. We are applying science and technology to solve complex mathematical equations for obtaining forecast based on current weather parameters using Numerical Weather Prediction (NWP) system. In this traditional system, it is required to utilize expensive, complex and high end computer power to obtain forecast. Sometimes, the forecasting obtain from NWP can be inaccurate which may have various catastrophic impacts in our society. Due to the dynamic nature of atmosphere, statistical techniques fail to provide good accuracy for weather forecasting.

Now a days, researchers are developing new models using different Machine learning and Deep learning algorithms for weather prediction, forecasting and climate analysis. The machine learning models which are implemented by different researchers are Random Forest classifier, Decision tree, Gradient Boosting Classifier, XGBoost, Gaussian Naïve Bayes model, Decision Tree, Multivariate linear regression (MLR), Logistic Regression, K-nearest neighbour (KNN) etc.

This paper review work gives a comparison of different techniques and algorithms used by researchers for weather prediction and climate analysis. Intention of this research work is to give an easy access to the techniques and algorithms used in the field of weather prediction and climate analysis.

Keywords: Weather Prediction, Numerical Weather Prediction (NWP), Weather Research and Forecasting (WRF), Machine learning, Deep learning, Artificial Neural Network.

1. INTRODUCTION

   Weather prediction is a process to know the conditions of the atmosphere at a specific location and time with the help of science and technology. It is the way of prediction of parameters of the atmosphere e.g. air temperature, pressure

   at sea level, humidity, wind, rainfall, snow etc. before they happen. Researchers are working for weather prediction from last two centuries. Weather prediction is the process of identifying and predicting to certain accuracy of the climatic conditions using different technologies or models. Many of our live systems depend on conditions of the weather to make necessary adjustments in their systems. Forecasting is useful to plan our activities and events. Weather prediction is one of the challenging tasks for meteorological scientists. In all the services provided by meteorological department, weather forecasting stands out on top of all the services across the globe.

   Traditional Weather forecasting models are sophisticated computer algorithms which are using mathematical equations to simulate and predict atmospheric conditions. These models are incorporating data from weather observations, satellite imagery, radar measurements, and other sources to create numerical representations of the Earth's atmosphere. Now a days different computing techniques or algorithms are available and we can use these algorithms for development of weather forecasting model and enhancing its accuracy.

   Section 2 gives background knowledge of weather prediction and forecasting.

   Section 3 gives literature review on various approaches or models or algorithms which are used for weather forecasting and climate analysis done by different researchers in todays era.

   Finally, section 4 presents the conclusion of this paper.

2. BACKGROUND

   Different categories of forecasting methods are Naive approach, Judgmental methods, Quantitative and Qualitative

   method, Econometric forecasting methods, Time series methods and Artificial intelligence methods. There are two widely used methods for weather forecasting which are Statistical models and NWP model. Nature of some parameters of weather data is linear and some other parameters are non-linear. Frequency, intensity and amount are main characteristics for time series weather data. These values can be varied from one position on earth to another position and from one time to another. Every statistical model has some drawbacks. The statistical approaches do not have the ability to identify nonlinear patterns and irregular trend in the time series.

   Because of that Machine Learning algorithms are used by the Researchers for development of weather forecasting models. The data are splitting into training and testing dataset, using 80% or 75% or 70% for training and remaining for testing. This study makes a review on Machine learning as well as Deep learning algorithms or models for weather forecasting.

3. LITERATURE REVIEW

   Surve et al. [1] have used four Deep learning models the CNN, RNN, LSTM and RBFN. Amongst all models the LSTM model showed the highest accuracy in weather forecasting, with an MAE of 0.734 and RMSE of 1.112. It suggests that deep learning models, particularly LSTM outperform NWP in accuracy and efficiency for weather forecasting. Sibuea and Maulana [2] have considered two Machine learning models i.e. Random forest(RF) and XGBoost. They observed that the XGBoost shows a lower RMSE value of 0.737, which is 0.753 in case of Random forest. Himavathi et al. [3] have used LSTM model and found that deep learning-based approaches exhibited superior performances over traditional statistical models, especially in capturing non-linear relationship and seasonal trends in the data. Kair et al. [4] have considered different Machine learning models i.e. Gradient Boosting, Random forest, ElasticNet, SGD Regressor, Bayesian Ridge, Support Vector Machine, CatBoost, Kernel Ridge Regression, XGBoost and LightGBM. They found that CatBoost, with MSE of 0.240 outperformed its counterparts Random forest with MSE of 0.602, XGBoost with MSE of 0.678 and LightGBM with MSE of 0.637. Jadon et al. [5] have used

   three Machine learning models i.e. Decision tree, Gradient Boosting and Bayesian Neural Network. They observed that Gradient Boosting classifier works well and gives accuracy of 96.66%. Choma et al. [6] have considered traditional numerical model such as Weather Research and Forecasting (WRF), Machine learning algorithms i.e. Support Vector Machine, Random Forest, XGBoost and Deep learning models such as LSTM. Finally they considered the combined (ensemble) and hybrid model e.g. Stacked Ensemble (SE) which combines the outputs of several algorithms, increasing the robustness and superior accuracy of the prediction upto 90-100%. Khatri and Rajani [7] have used different Machine learning models i.e. RF, XGBoost, SVM, LSTM and Polynomial Regression. They observed that the LSTM shows the best result with accuracy upto 80.11%. Faulina et al. [8] have considered three models i.e. LSTM, LSTM Conv1D and LSTM GRU. They found that the model LSTM GRU outperformed the other models with RMSE value 0.473 with ste size 20. Lakshmaiah et al. [9] have utilized the historical data of weather parameters from surrounding areas of a particular city to predict its weather condition. They found that Random Forest Regressor is the superior repressor, as it ensembles multiple decision trees while making decision. Jayasingh et al. [10] have considered different Machine learning models and observed that the accuracy of the Gradient Boosting model is upto 81.67%. They have planned to use different IoT devices to collect the exact data of weather parameters so that the dataset to be used in the model will be more exact as well as the performance of the model will be more accurate accordingly. Patkar et al. [11] have used different Machine Learning Techniques for weather prediction and found that Naive Bayes Bernoulli produces the best weather prediction results upto 100% accuracy. In future, they intend to use more low-cost devices such as temperature and humidity sensors etc. Basha et al. [12] have used two Deep Learning algorithms i.e. Multi-layer Perceptron (MLP) and Auto- encoder. They used an architecture, where inputs of the Auto-encoder network are connected to the MLP using a sigmoid function. They observed that because of nonlinear relationships in rainfall datasets and the ability to learn from the past, Artificial Neural Network makes a superior solution to all approaches they used. Liyew, C. M., &

   Melese, H. A. [13] have used three machine learning algorithms i.e Multivariate Linear Regression (MLR), Random Forest (RF), and XGBoost. The comparison of results among the three algorithms shows that the XGBoost is a better-suited machine learning algorithm for daily rainfall amount prediction using selected environmental features. Hewage et al. [14] have used Artificial Neural Network model Long Short-term Memory (LSTM) and Temporal Convolutional Network (TCN). The authors developed two deep learning models i.e. multi-input multi- output (MIMO) and multi-input single-output (MISO). The model outperformed the state-of-the-art WRF model up to 12 hour for 10 surface weather parameters. The model is able to overcome some challenges within the WRF model, like the understanding of the model and its installation, as well as its execution and portability. Zenkner, G., & Navarro-Martinez, S. [15] have used Bi- LSTM Model. The model is tested using historical data of two London- based locations i.e. Kew Garden and Heathrow to train a Bi-LSTM Recurrent Neural Network to predict temperature and relative humidity. The results show that predictions up to three days have accuracy comparable to expensive Numerical Weather Predictions. Salman et al. [16] have considered three models using Deep learning algorithms such as CRBM and CNN and then compared with the Recurrent Neural Network (RNN), a prominent time series weather forecasting model. Roy, D. S. [17] has considered three Deep learning algorithms which are MLP, LSTM and a combined model of CNN and LSTM for development of a model for prediction of air temperature based on data collected from John F. K. International Airport. He found the prediction result shown by the combination model of CNN and LSTM have better accuracy upto 97.42% and 71.58% for prediction before 1 day and 10 days respectively. Kumar et al. [18] have used four algorithms i.e. Logistic Regression, KNN, Decision Tree and Random Forest. They found that the most efficient of these algorithms are Random Forest and KNN which give us the accuracy of approximately 88% and 87% respectively. Raheem et al. [19] have used Decision Tree (DT), K-nearest Neighbor (k-NN) and Logistic Regression. The Decision tree model, which has upto 100% accuracy rate, outperforms

   the Logistic Regression, which has a 93% accuracy rate. This study achieved an appropriate label of accuracy from the Decision tree model in terms of rain prediction. Bharathi, K. S., & Babu, B.S. [20] have used Random Forest Regressor, Linear Regressor and Decision Tree Regressor. An algorithm known as Learning based Intelligent Weather Forecasting (LIWF) is proposed and implemented. They found that highest performance is exhibited by RF regression model with 96.45% accuracy. Oshodi, I. [21] has used Random Forest, Decision Tree, Gaussian Naïve Bayes and Gradient Boosting. It is observed that the Gaussian Naive Bayes model gives more accurate result which is 84.15% of the implemented algorithms. The result of the model provided accurate prediction and useful guidance for meteorologist in their operational forecasting duties. Balan et al. [22] have used Artificial Neural Network and found that ANN works well with preprocessed and normalized data. The correlation between the attributes defines the influence on the prediction of any system. Iliyas et al. [23] have compared the use of four different machine learning models i.e. Random Forest, Linear Regression, Decision Tree and Ridge. DT outperforms all the models based on performance metrices. This model can be used for real-life applications to improve our daily life activities. Mahajan et al. [24] have considered Artificial Neural Network algorithm. They have reviewed different models for weather forecasting and recommended ANN with back propagation for weather forecasting.

   A comparison of different approaches done by different authors for weather prediction and forecasting is shown in the Table 1. The comparison is based on the following parameters: authors, technology or algorithms, dataset, weather attributes, accuracy and the result of accuracy.

   Table-1: Comparison of different approaches or algorithms for Weather Prediction

   RF68.14,

   XGBoost65.65 SVM70.96,

   LSTM80.11

   Poly. Reg69.89

   Authors	Technology/ Algorithms	Dataset	Weather Attributes	Accuracy measure	Result of accuracy in the respective model
   Surve et al. (2025) [1]	CNN, RNN, LSTM, RBFN	Dataset (2006- 2016) collected from Kaggle	Temp, Pressure, Humidity	MAE, RMSE	MAE CNN0.918 RNN0.755 LSTM0.734 RBFN1.408 NWP1.198	RMSE CNN1.333 RNN1.149 LSTM1.112 RBFN2.234 NWP1.502
   Sibuea and Maulana (2025) [2]	RF, XGBoost	Dataset (01-04- 2021 to 31-03- 2024)	Temp, Humidity, Wind speed	RMSE, R2	RMSE RF0.753 XGBoost0.737	R2 RF0.736 XGBoost0.747
   Himavathi et al. (2025) [3]	LSTM	Dataset (Jan2009 to Aug 2016)	Temp, Humidity, Pressure, Wind speed	MSE	0.124 (for epoch 10)
   Kair et al. (2025) [4]	GB, RF, CatBoost, XGBoost, LightGBM	Dataset of Almaty city	Dew point, Humidity, Pressure at Sea level, Pressure at Station level, Max Temp, Min Temp	MSE	GB0.740 RF0.602 CatBoost0.240 XGBoost0.678 LightGBM0.637
   Jadon et al. (2025) [5]	DT, GB, BNN	Dataset (not specified)	Precipitation, Max Temp, Min Temp, Wind speed, Date, Weather	Accuracy	DT86.13 GB96.66 Bayesian NN89.73
   Choma et al. (2025) [6]	SVM, LSTM, WRF, Stacked Ensemble	Dataset (500000 points) of Sliac Military Airport	Visibility, Temp, Humidity, Pressure, Satellite image for cloud and moisture	Accuracy	SVM70-80% LSTM80-90% WRF60-70% Stacked Ensemble90-100%
   Khatri and Rajani (2025) [7]	RF, XGBoost, SVM, Poly Reg, LSTM	Dataset (2009- 2023) of Mumbai, Pune etc. collected from Kaggle	Sunlight, Date-time, Pressure, Precipitation, Max Temp, Min Temp	Accuracy
   Faulina et al. (2024) [8]	LSTM, LSTM-Conv1D, LSTM-GRU	Dataset (Jan 2024 to Jan2022) of Jakarta	Air Temperature	RMSE	LSTM2.326 LSTM Conv1D2.338 LSTM GRU0.473
   Lakshmaiah et al. (2023) [9]	RF, Ridge, SVM, MLP, ETR	Dataset from Nashville city	Temperature	RMSE	Ridge 4.0, MLP high RF 3.0, ET 3.0
   Jayasingh et al. (2022) [10]	DT, RF, SVM, KNN, GB, Adaboost, Xgboost, NB and Logistic R	Dataset (1996- 2017)	Temp, Dew, Humidity, Pressure, Visibility, Wind	Accuracy	DT 71.23, RF 79.52 SVM 59.33. KNN 77.86 Adaboost71.43, XGB79.94 GB81.67, Naïve Bayes73.09 Logistic R78.14
   Patkar et al. (2021) [11]	DT, ANN, NBN, SVM, Fuzzy Logic, RBT and GA	Dataset (not specified)	Min Temp, Max Temp, Humidity, Rainfall, Sunshine, Evaporation, wind gust/direction/ speed, air pressure, cloud	Accuracy	Naïve Bayes B1.00 Logistic R0.99 Naïve Bayes G0.95 KNN0.88
   Basha et al. (2020) [12]	MLP and Auto- encoder	Dataset (not specified)	Rainfall	MSE, RMSE	Values are not shown.
   Liyew, C. M., & Melese, H. A. (2021) [13]	MLR, RF, and XGBoost.	Dataset (1999- 2018) of Bahir Dar City, Ethiopia	Year, Month, Date, Min Temp, Max Temp, Humidity, Rainfall, Sunshine, Evaporation, wind speed	MAE, RMSE	MAE: RF 4.49 MLP4.97 XGB3.58	RMSE: RF 8.82 MLP8.61 XGB7.85
   Hewage et al. (2021) [14]	LSTM and TCN	Dataset (Jan 2018 to May 2018) with 12 parameters	TSK, PSFC, U10, V10, Q2, Rain, Snow, TSLB, SMOIS	MSE	Values are calculated for 12 weather parameters separately. LSTM better in comparison with TCN
   Zenkner, G., & Navarro- Martinez, S. (2023) [15]	Bi- LSTM	Dataset (2015- 2021) of Kew Gardens and Heathrow, London	Temp, Relative humidity	MAE, RMSE	MAE (average) Kew G11.1 Heathrow10.9	RMSE (average) Kew G14.5 Heathrow14.0
   Salman et al. (2015) [16]	CRBM and CNN	Dataset (1973 to 2009) in Aceh area	Max Temp, Min Temp, Precipitation, Relative Humidity, Sea level Pressure, Wind, Rainfall	RMSE	Values not shown

   Roy, D. S. (2020) [17]	MLP, CNN, combination of CNN and LSTM	Dataset (01/01/2009 – 01/01/2019) for John F. K. International Airport, NY	Temp, Humidity, Air pressure, Wind speed, Precipitation, Snowfall	MAPE	1 day ahead prediction: MLP89.15%, CNN95.03% CNN+LSTM 97.42%	10 days ahead prediction: MLP63.23%, CNN70.32% CNN+LSTM 71.58%
   Kumar et al. (2022) [18]	RF, DT, Logistic Regression, KNN	Dataset (not specify)	Date, Location, Temp, Humidity, Air pressure, Wind speed, Precipitation	Accuracy, Precision	Accuracy (%): RF88.21 KNN87.36 DT73.67 LR84.63	Precision: RF0.84 KNN0.79 DT0.16 LR0.73
   Raheem, M. A. et al (2022) [19]	DT, k-NN and Logistic Regression	Dataset (49 years) from Seattle-Tacoma International Airport	Day, month, Precipitation, Temp Min, Temp Max, Rain.	Accuracy, Precision	Accuracy (%): DT100, KNN78.10 LR93	Precision: DT1.00, KNN0.76 LR0.98
   Bharathi, K. S., & Babu, B. S. (2023) [20]	RF, Linear Regression and DT	Dataset (2020)	Temp, Pressure, Relative Humidity, Precipitation	Accuracy, MAE	Accuracy (%): Linear R96.29 DT93.37 RF96.45	MAE: Linear R5.34 DT8.60 RF4.68
   Oshodi, I. (2022) [21]	RF, DT, GNB, GB	Dataset (1st Jan 2012 to 31st Dec 2015) of Seattle town collected from Kaggle	Drizzle, Rain, Sun, Snow, and Fog	Accuracy	RF79.50 GB80.87 GNB84.15 DT72.40
   Balan et al. (2019) [22]	ANN	Dataset (1978- 2017) of Thiruvanthapura m region	Temp, Pressure, Rel. Humidity, Wind speed, Precipitation	MSE	Normalisation dataset perform better
   Iliyas et al. (2022) [23]	Linear Regression, SVM, Ridge, DT, RF	Dataset (96453 data points) of 11 parameters collected from Kaggle	Temp, Humidity, Air pressure, Wind speed, Cloud cover, Precipitation, Visibility	RMSE, MSE, MAE	RMSE: DT0.038, LR0.759 RF0.226, Ridge0.575 MSE: DT0.001, LR0.576 RF0.051, Ridge0.576 MAE: DT0.010, LR0.604 RF0.051, Ridge0.604
   Mahajan et al. (2017) [24]	ANN	Dataset (3 years) collected from Met Dept.	Temp, Rel. Humidity, Air pressure, Wind speed and direction, Cloud amount and height, Rainfall	MSE	Value not shown

   RFRandom Forest, DTDecision Tree, SVMSupport Vector Machine, GBGradient Boosting, MLRMultivariate Linear Regression, MLPMulti-Layer Perceptron (MLP), ETRExtra-Tree Regression, KNNK-nearest Neighbour, XGBoostExtreme Gradient Boosting, GNBGausian Naive Bayes, NBNaive Bayes, NBNNaive Bayes Networks, BNNBayesian Neural Network, WRFWeather Research and Forecasting, ANNArtificial Neural Network, RNNRecurrent Neural Network, CNNConvolutional Neural Network, TCN Temporal Convolutional Network, RBTRule-based Techniques, GAGenetic Algorithms, LSTMLong Short-Term Memory Network, RBFNRadial Basis Function Networks, DLDeep Learning, CRBMConditional Restricted Boltzmann Machine, MAE Mean Absolute Error, MSE Mean Squared Error, RMSE Root Mean Squared Error, R2 Coefficient of Determination.

4. CONCLUSION

The prediction of weather has great importance to take necessary preventive measures to stop the damages to life and property to a large extent. Quantitative forecast like temperature, humidity and rainfall are important in agriculture area as well as to traders within commodity markets. Temperature forecasts are used by utility companies to estimate demand over coming days. Again outdoor activities are severely restricted by heavy rain,

snowfall and chill. After review it is found that Random forest, Decision tree, Support vector machine, Multivariate linear regression, XGBoost algorithms are mostly used by Researchers for development of weather prediction model. Further, some other researchers are developing weather forecasting models using deep learning algorithms like ANN, RNN, CNN, Long Short-Term Memory (LSTM), Multi-layer Perceptron, Auto-encoder etc. This paper presented a review of different algorithms or models used

for weather forecasting and problems one might encounter while applying different approaches for weaher forecasting. Due to linear as well as non-linear relationships in weather parameters and ability of learning from the past makes Deep learning approaches are preferable approach from all available approaches.

REFERENCES:

1. Surve, R.B., Lanjewar, U.A., & Rewatkar, L.R. (2025). Deep learning and NWP: an evaluation for accurate weather forecasting. Indian Journal of Science and Technology, ISSN: 0974-6846 (print).

2. Sibuea, R.U., & Maulana, H. (2025). Comparison of random forest and XGBoost methods on weather in north Sumatera. TSABIT journal of computer science, https://doi.org/10.56211/tsabit44.

3. Hymavathi, M., Kumar, S.K., & Jahnavi, Y. (2025). Predictive modelling of meteorological data using time series methods. International journal advanced networking and applications, 16(6), 6677-6682, ISSN: 0975-0290.

4. Kair, D., Baktygaliyev, A., Kassymova, A., Joldybayev, A., Ramazan, N., & Kartbayev, A. (2025). Advancing information systems for smart decision making using machine learning-based weather prediction. Journal of information systems engineering and management, 10(24s), E-ISSN:2468-4376.

5. Jadon, T., Pachauri, P., & Warsi, A. (2025). Predict weather with machine learning. International journal on science and technology, E-ISSN: 2229-7677.

6. Choma, L., Kelemen Jr, M., Antosko, M., Ozdincova, K., & Sabo,

   J. (2025). Prediction of hazardous weather phenomena using artificial intelligence. Acta Avionica, XXVII 52(1), DOI: 1035116/aa.2025.0006.

7. Khatri, S., & Rajani, P.K. (2024, Dec). Advanced weather forecasting with machine learning: Leveraging meteorological data for improved predictions. Communications on applied nonlinear analysis, 32(5s), ISSN:1074-133X.

8. Faulina, R., Nuramaliyah, & Safitri, E. (2024). Air temperature prediction system using long short-term memory algorithm. REKAYASA 17(3), 463-473, ISSN:0216-9495 (Print).

9. Lakshmaiah, D., Satyanarayana, L., Rahman, MD., Anusha, G., Mamatha, U., Reddy, V.D., & Hemanth, P. (2023, July-Dec). Machine Learning using Smart Weather Forecasting. Industrial Engineering Journal, 52(2), ISSN:0970-2555.

10. Jayasingh, S. K., Mantri, J. K., & Pradhan, S. (2022, May). Smart Weather Prediction using Machine Learning. https://www.researchgate.net/publication/360365118

11. Patkar, U., Maske, S., Ahmad, S., Mengade, R., & Sadawarti, G. (2021). Weather Prediction using Machine Learning. GIS Science Journal, 8(12), ISSN No 1869-9391.

12. Basha, CMAK, Z., Bhavana, N., Bhavya, P., & Sowmya, V. (2020). Rainfall Prediction Using Machine Learning & Deep Learning Techniques. Proceedings of the International Conference on Electronics and Sustainable Communication Systems (ICESC 2020) IEEE Xplore Part Number: CFP20V66-ART; ISBN: 978-1-

    7281-4108-4

13. Liyew, C. M., & Melese, H. A. (2021). Machine learning techniques to predict daily rainfall amount, Journal of Big Data, 8:153 https://doi.org/10.1186/s40537-021-00545-4

14. Hewage, P., Trovati, M., Pereira, E., & Behera, A. (2021). Deep learning-based effective fine-grained weather forecasting model. Pattern Analysis and Applications, 24:343366, https://doi.org/10.1007/s10044-020-00898-1

15. Zenkner, G., & Navarro-Martinez, S. (2023). A flexible and lightweight deep learning weather forecasting model. Applied Intelligence, 53:2499125002, https://doi.org/10.1007/s10489- 023-04824-w

16. Salman, A. G., Kanigoro, B., & Heryadi, Y. (2015). Weather Forecasting using Deep Learning Techniques. International Conference on Computer Science and Computational Intelligence (ICCSCI 2015), www.elsevier.com/locate/procedia

17. Roy, D. S. (2020). Forecasting The Air Temperature at a Weather Station Using Deep Neural Network. 9th International Young Scientist Conference on Computational Science (YSC 2020), www.elsevier.com/locate/procedia

18. Kumar, V., Yadav, V.K., & Dubey, S. (2022, May). Rainfall Prediction using Machine Learning. International Journal for Research in Applied Science & Engineering Technology (IJRASET), 10(V), 2494-2497, ISSN: 2321-9653, www.ijraset.com

19. Raheem, M. A., Awotunde, J. B., Adeniyi, A. E., Oladipo, I. D., & Adekola, S. O. (2022, December). Weather prediction performance evaluation on selected machine learning algorithms. IAES International Journal of Artificial Intelligence (IJ-AI), 11(4), 1535~1544, ISSN:2252-8938.

20. Bharathi, K. S., & Babu, B. S., (2023, August). AIWFF: A Machine Learning based Framework for Automatic Weather Forecasting. International Journal on Recent and Innovation Trends in Computing and Communications, 11(9), ISSN: 2321- 8169.

21. Oshodi, I. (2022, July). Machine Learning-Based Algorithms for Weather Forecasting. International Journal of Artificial Intelligence and Machine Learning, 2(2), 12-20, ISSN: 2789-2557.

22. Balan, M..S, Selvan, J. P., Bisht, H.R., Gadgil, Y.A., Khaladkar, I.R., Lomte, V.M. (2019). Rainfall prediction using deep learning on highly non-linear data. International Journal of Research in Engineering, Science and Management. 2(3), 590592, E-ISSN: 2581-5792.

23. Iliyas, I. I., Umoru, A., Chahari, A. E., Garba, M. M. (2022, October). Performance Evaluation of Machine Learning Models for Weather Forecasting. Journal of Artificial Intelligence and Systems, 4, 22-32, E-ISSN: 2642-2859.

24. Mahajan, P., Nawale, C., Kini, S., Shinde, K. (2017). Weather Forecasting using Neural Network. International Journal of Engineering Research & Technology, ISSN: 2278-0181, www.ijert.org

25. Parmar, A., Mistree, K., & Sompura, M. (2017, March). Machine Learning Techniques for Rainfall prediction: A Review. International Conference on Innovations in information Embedded and Communication Systems, https://www.researchgate.net/publication/319503839

26. Bhawsar, M., Tewari, V., & Khare, P. (2021, July). A Survey of Weather Forecasting based on Machine Learning and Deep Learning Techniques. International Journal of Emerging Trends in Engineering Research, 9(7), ISSN: 2347-3983.

27. Bochenek, B., & Ustrnul, Z. (2022). Machine Learning in Weather Prediction and Climate Analysis-Applications and Perspectives. Atmosphere, https://doi.org/10.3390/atmos13020180.

28. Ray, S. (2019). A quick review of machine learning algorithms. (2019). International conference on machine learning, big data, cloud and parallel computing (COMITCon), 35-39, IEEE, doi: 10.1109/COMITCon.2019.8862451.