Weather is the condition of the atmosphere and forecasting is predicting the condition of the atmosphere in near future. Weather forecasting is a formidable challenge as weather is a multi-dimensional, continuous and chaotic process. The distinct nature of the model forecasting in all situations accurately is challenging. Presently weather conditions are being obtained from satellites, Doppler radar, radio sounds, observations from aircraft and ground. Collected data is subjected to various statistical and machine learning techniques. These techniques can incorporate relatively simple observation of the sky to highly complex computerized mathematical models. Weather forecasting still remains a challenging issue, due to unpredictable and chaotic nature of weather. Even with present methods the weather forecasting system may still fail to predict weather attribute, therefore there is still scope left to improve these systems. The objective of carrying out the survey is to look forward on how machine learning can help us to improve weather parameter estimation. In this paper we report the different methods carried out by leading researchers, formidable challenges and present our views on development of efficient weather forecasting system. Also, we propose a method which makes use image processing and neural networks to achieve the weather parameter estimation.

Predicting rainfall is an important step in generating data for climate impact studies. Rainfall predictions are a key process for providing climate impact assessments with inputs. A consistent rainfall pattern is typically good for normal plants; nevertheless, too much or too little rainfall can be disastrous to crops, even deadly. Drought can damage plants and lead to erosion, while heavy rainfall can encourage the growth of destructive fungi. Machine Learning (ML) can be helpful in overcoming such issues; for example, ML can be used to predict rainfall and apply it to foresee crop health and yield. Predictive analysis is a subset of data mining that forecasts future probabilities and patterns. Various sectors like the Agricultural Produce Markets Committee (APMC), Kisaan call centre, etc., can use proposed method, enabling the sector and farmers to obtain information on future precipitation, crop yields and crop health.

Artificial Intelligence (AI) and especially Machine learning (ML) is finding to be useful in many tasks that are simple to carryout to complex tasks that are found to be challenging in nature. One such application of ML is in classification of images. In this paper an attempt to blend the application of unsupervised ML (k-means clustering) approach along with content based image retrieval (CBIR) approach is presented to classify clouds. K-means is a simple approach which can be applied for image classification, also k-means easily adapts to new examples of classification. An attempt is made to combine the features of k-means and CBIR to classify the cloud images. It is performing a double check on the cloud image being classified. Clustering in included with CBIR to obtain an easy retrieval of cloud image. Three categories are chosen for classification-low level clouds, high level clouds and medium level clouds. The classification of clouds is achieved with the help of ground based images (or whole sky images). High resolution of ground based images can be obtained with the help of new high resolution cameras. These ground based images are processed to classify the clouds present in the images into the three categories as mentioned above. Ground based images captured by ground based cameras provide better ground truth. The results find its application in various domains such as agriculture, aviation, military, and various meteorological applications.