Rana, PushpendraFleischman, ForrestRamprasad, VijayLee, Kangjae2020-03-262020-03-262020-03-26https://hdl.handle.net/11299/212261Data are derived from publicly released data produced by the forest department of the Government of Himachal Pradesh, India. Dataset-A comprising of 16,674 forest polygon is the result of a 4 year effort on the part of the Himachal Pradesh forest department, and covers 33 forest divisions of Himachal Pradesh. We could not use 1998 polygons in this dataset due to missing data. The digitization of polygons for the rest of the 10 forest divisions in the state of Himachal Pradesh is in process. The data has 31 predictor variables used in training a predictive model to estimate tree cover loss probabilities in these compartments based on ensemble-modeling. Outcome variable included in the dataset is tree cover loss/mortality (dummy; mortality =1, No mortality =0). Predictor variables include variables related to forest dependence, soil and biophysical characteristic, canopy cover and other management practices. For details about prediction algorithm model construction and model predictors, please refer to the readme section. Dataset-B comprises of 2147 forest polygons where plantations happened from 1 st Jan 2016 to 31 st July, 2019. Total 2809 tree plantations were carried out during this period. But, due to missing data, we could only use 2147 for construction of data. Finally, for our paper (under review), we used 2024 tree plantations for which we had budgetary data available. The dataset also has same predictor variables as in dataset-A. We used our selected ensemble model to predict tree cover loss probabilities for 2024 tree plantations and then compared budgetary allocations against these probabilities for our analysis.This dataset provides information on the tree plantation programs of the government of the state of Himachal Pradesh, India. Data were released publicly by the government in response to questions posed by Members of the State Legislative Assembly in 2019. We combined this data with other publicly available datasets to provide a more complete picture of plantation programs for the purpose of evaluating their effectiveness.CC0 1.0 UniversalIndiaHimalayastree plantationsafforestationDatasethttps://doi.org/10.13020/8x0d-gb23