PV adoption

This code is just for visualizing the findings rather than running model.

Load packages

Load Data

load("dat_new2.RData")

Visualize vermont causal flows

gn_vm

• The center and northeast parts have low density of causal links due to the mountainous geography.
• Dense causal links with bi-directionality exist in the northwest region where urbanized areas are located.
• Neighborhood diffusion–within tract diffusion of PV adoption–occurs strongly in Burlington area (the most populated northwestern region), identified by high mutual information. Other areas with high mutual information tend to be those with high population density.

Visualize Seattle causal flows

gn_sea

• Rivers hinder PV adoption diffusion across tracts are contiguous.
• It is less likely to have mutual causal links.

SEATTLE

par(mfrow = c(1, 2))
varImpPlot(rf.tree.sea.out,main = "Seattle, Out TE")
varImpPlot(rf.tree.sea.out_w,main = "Seattle, Weighted Out TE")

Focus on those which spread out rooftop PV - Dependent variable: % of out-going causal connections among neighboring tracts - Housing-related variables such as SingleFamily, HomeOwn are more important than economic variables (wealth, income) - Inclination to adopt technology from diverse tracts is important on spreading rooftop PV to more diverse tracts (Ininfoa). - Neighborhood diffusion is not critical on spreading-out behaviors. - How clustered the adoption occurs is not important (Clustered)

par(mfrow = c(1, 2))
varImpPlot(rf.tree.sea.in,main = "Seattle, In TE")
varImpPlot(rf.tree.sea.in_w,main = "Seattle, Weighted In TE")

Focus on those which spread in rooftop PV - Dependent variable: % of in-coming causal connections among neighboring tracts - How risked you are from natural disasters becomes important for those who are adopting rooftop PV (RiskScore) - Neighborhood diffusion is not critical on spreading-in behaviors. - How clustered the adoption occurs is not important (Clustered)

par(mfrow = c(1, 2))
varImpPlot(rf.tree.sea.mi,main = "Seattle, MI")
varImpPlot(rf.tree.sea.mi_w,main = "Seattle, Weighted MI")

Focus on those which self-loop rooftop PV - Dependent variable: existence of self-reinforcing adoption within a tract - Housing related variables are still important - Self-reinforcement is quite independent from tract-tract spreading (decoupled)

VERMONT

par(mfrow = c(1, 2))
varImpPlot(rf.tree.vm.out,main = "Vermont, Out TE")
varImpPlot(rf.tree.vm.out_w,main = "Vermont, Weighted Out TE")

par(mfrow = c(1, 2))
varImpPlot(rf.tree.vm.in,main = "Vermont, In TE")
varImpPlot(rf.tree.vm.in_w,main = "Vermont, Weighted In TE")

par(mfrow = c(1, 2))
varImpPlot(rf.tree.vm.mi,main = "Vermont, MI")
varImpPlot(rf.tree.vm.mi_w,main = "Vermont, Weighted MI")