Nita H. Shah1 <br/><br/>
Machine learning-based verification of satellite weather alerts for heavy rainfall in Ladakh 

 - pp63-69 
<br/><br/> The present study investigates heavy rainfall patterns<br/>and their variability in Ladakh by using K-means clustering with the Apriori algorithm, which uncovers<br/>the co-occurrence pattern of heavy rainfall alerts obtained from the ISRO MOSDAC portal. The proposed<br/>algorithms reveal that location (lat.: min. = 32.82,<br/>max. = 35.71; long.: min. = 77.59, max. = 79.91)<br/>and location (lat.: min. = 33.11, max. = 35.76; long.:<br/>min. = 75.82, max. = 77.75) exhibit the highest confidence (79.55%) and frequency (48.61%) among all<br/>patterns, indicating strong interdependencies. This<br/>suggests that the alerts in one location can potentially impact the other, offering actionable guidance<br/>for disaster preparedness. The present study highlights a significant match between predicted alerts and<br/>actual heavy rainfall events, underscoring the utility<br/>of machine learning in refining weather alert systems 
<br/><br/><label>Subjects--Facted Index Terms: </label><br/>Apriori algorithm<br/>disaster management<br/>heavy rainfall alert<br/> K-means clustering.