Studies on population of leaf miner (Liriomyza trifolii) in tomato (Solanuml ycopersicum Linnaeus) compared with weather data was carried out for eight consecutive years (2011-18) during kharif season. The weather variables considered are maximum & minimum temperature (MaxT & MinT) (0C), morning and evening humidity (RHM & RHE) (%), sunshine hours (SS) (hr/d), wind velocity (Wind) (km/hr), total rainfall (RF) (mm) and rainy days (RD). The study concluded that the comparatively average population of leaf miner in experimental protected field was found higher than the other (1.3 Nos/5 larvae/plant) during 31 SMW in 2012 followed by farmer’s field, and the lowest pest population (0.1 Nos/5 larvae/plant) was recorded in experimental unprotected field during in the 2016. Correlation analyses indicate while both current and one lag wind and RainyD had negative and positive influence respectively MinT and RHE had negative influence on leaf miner incidence. Among all variables, MaxT (current) and Rainy D (current and one lag) had highly significant positive effect on leaf miners. Machine learning techniques namely support vector regression (SVR), random forest (RF) and the other statistical models e.g., multiple linear regression (MLR), General regression neural network (GRNN), and Feed forward neural network (FFNN) are used. An empirical comparison of the above models is carried out based on root mean square error (RMSE). It is observed that, for leaf miner, the RMSE values of RF less as compared to other competing models. To this end, Diebold-Mariano (D-M) test was applied for comparison of forecasting performance among the applied models. It is observed that, in the studied pest, predictive accuracy of RF is higher than that of other models. The analysis is carried out using R package