The　proportion　of　buildings　occupying　underground　space　has　increased　with　three-dimensional　urban　development.　Thermal　comfort　is　crucial　to　the　design　of　underground　spaces　and　plays　an　important　role　in　the　optimization　of　building　environment　controls.　Owing　to　limitations　in　recording　various　practical　environmental　parameters,　it　is　difficult　to　access　large　data　and　further　to　establish　an　accurate　forecasting　model　for　the　thermal　comfort　of　an　underground　space.　This　paper　addresses　the　problem　from　the　perspective　of　data　enhancement.　A　model　for　generating　underground　space　data　based　on　a　variational　autoencoder　is　proposed.　The　model　maps　data　of　the　thermal　comfort　of　an　underground　space　to　a　highly　compressed　latent　layer　space　and　generates　data　in　an　unsupervised　manner.　The　forecasting　models　were　trained　using　the　generated　data,　resulting　in　accuracy　improvements　of　41.34%-45.31%.　Hence,　the　proposed　generative　model　can　learn　effective　real　data　features.　The　results　also　demonstrate　that　the　adjustment　of　ventilation　is　more　effective　than　the　adjustment　of　the　temperature　and　relative　humidity　in　improving　the　thermal　comfort　of　an　underground　space.　The　findings　of　this　research　will　provide　better　thermal　comfort　evaluation　for　the　operational　management　of　building　environment　in　underground　spaces.