|
hong kong |
7 |
|
beijing |
6 |
|
deep learning |
6 |
|
air pollution modelling |
4 |
|
environmental injustice |
4 |
|
high spatial resolution |
4 |
|
pm2.5 pollution |
4 |
|
social deprivation index |
4 |
|
air pollution control regulation |
3 |
|
air pollution control regulations |
3 |
|
air pollution forecast |
3 |
|
air pollution monitoring |
3 |
|
air quality |
3 |
|
artificial intelligence |
3 |
|
bayesian deep-learning |
3 |
|
bayesian lstm |
3 |
|
big data |
3 |
|
blue sky day |
3 |
|
china |
3 |
|
city-wide |
3 |
|
citywide domain-specific information |
3 |
|
clean air act |
3 |
|
climate policy |
3 |
|
cnn-lstm |
3 |
|
coal |
3 |
|
computational social science |
3 |
|
counterfactual analysis |
3 |
|
data interpretability |
3 |
|
data privacy and security |
3 |
|
domain-specific knowledge |
3 |
|
effects of regulatory interventions |
3 |
|
energy policy |
3 |
|
environmental inequality |
3 |
|
fine-grained air pollution estimation and forecast |
3 |
|
fine-grained resolution |
3 |
|
geo-coded tweets |
3 |
|
health and well-being improvement |
3 |
|
health management |
3 |
|
household wealth proxies |
3 |
|
international movement |
3 |
|
low-cost sensor |
3 |
|
machine learning |
3 |
|
met-resnet-lstm |
3 |
|
multi-task learning |
3 |
|
personalization |
3 |
|
pm (1.0,2.5) |
3 |
|
pm2.5 and pm₁₀ estimation |
3 |
|
pollution |
3 |
|
portable sensor node |
3 |
|
prediction fusion |
3 |
|
prediction uncertainty |
3 |
|
propensity score |
3 |
|
resnet-lstm |
3 |
|
resnet-lstm-sp |
3 |
|
saliency analysis |
3 |
|
sensor calibration |
3 |
|
short-term happiness |
3 |
|
smart behavioural intervention |
3 |
|
socio-economic status |
3 |
|
spatial-temporal data |
3 |
|
station-wide |
3 |
|
street canyon effect |
3 |
|
subjective well-being prediction |
3 |
|
traffic congestion |
3 |
|
traffic speed |
3 |
|
transfer calibration |
3 |
|
twitter users |
3 |
|
united kingdom |
3 |
|
comprehensive assessment |
2 |
|
discourse analysis |
2 |
|
nuclear safety |
2 |
|
post-fukushima |
2 |
|
pre-fukushima |
2 |
