Abstract : Malnutrition has become a significant public health challenge strongly associated with the substantial increase in the risk of mortality and morbidity in children. This study will be conducted to determine the geographical variation in nutritional status of under-five children and identify the spatial clusters based on demographic and household characteristics in Karkala taluk of Karnataka state, India, and replicate the same in other areas. The aggregated nutrition status data of children under five years are collected from the Udupi district health office for three years, validated at the village level. The anthropometry, topography, and socio-demographic data is collected by visiting the household. The retrospective discrete Poisson probability model will identify the clusters of underweight, stunting and wasting. Spatial autocorrelation statistics like Local Indicators of Spatial Association (LISA) statistics of nutritional status will be analysed. The logistic regression model will be used to analyse the causes of clustering. The geo-coordinates of the households were summarised using a Cartesian coordinate system. The SaTScan statistic software (SaTScan v10.0.2) will be used to identify the spatial, Spatio-temporal clusters of underweight, stunting and wasting among under-five children. This software will detect the randomness of nutritional status of under-five children over space and space-time. The spatial data analysis and spatial autocorrelation will be carried out using GeoDa software. Spatial dependence of nutritional status will be analysed through the Global Moran's Index and Local Indicators of Spatial Association (LISA). The observed and expected cases inside the window are considered for spatial and space-time cluster significance in SaTScan software. The LISA statistics will indicate the local pockets of non-randomness or hot spots. The LISA statistic is also used to assess the contribution of location on the magnitude of global figures. The Spatiotemporal and autocorrelation results can be used for risk analysis of malnutrition among under-five children by the policymaker for decision making.