[KongchangAI]
ModelDySENSE 框架

DySENSE

A multimodal generative-AI framework for urban energy consumption data generation that decouples static urban morphology from dynamic monthly energy consumption and jointly generates spatially aligned satellite imagery and energy consumption maps, supporting downstream tasks such as energy-efficient urban planning and building performance simulation.

Timeline (last 90 days)

Nov 16

The DySENSE framework decouples urban problems into long-term stable urban form (static layer) and monthly energy consumption that fluctuates with seasonal climate (dynamic layer).

Unverified50%
Nov 16

DySENSE supports two conditional generation settings: conditioned on static land use, generating realistic and spatially aligned satellite imagery and energy consumption maps; and conditioned on monthly and climate prompts, keeping urban form unchanged and jointly generating only dynamic monthly energy consumption maps.

Unverified50%
Nov 16

DySENSE adopts multimodal joint generation, outputting multiple spatially aligned results (satellite imagery and energy consumption maps) in a single forward pass rather than staged serial generation.

Unverified50%
Nov 16

The main technical difficulty of DySENSE is the inter-modality alignment constraint: building outlines in satellite imagery must be pixel-level consistent with high-value regions in energy consumption maps.

Unverified50%
Nov 16

DySENSE was validated on four cities: New York, Washington, Norfolk, and Busan.

Unverified50%
Nov 16

Using less than 25% of labeled data, DySENSE can generate labeled high-fidelity synthetic energy consumption data and improve downstream prediction performance by 8% mIoU.

Unverified50%
Nov 16

Compared with existing methods, DySENSE improves prediction performance by 8.7% (accuracy) and reduces prediction error by 9%–18% (CVRMSE, ASHRAE standard).

Unverified50%
Nov 16

DySENSE's application directions include energy-efficient urban planning, peak load analysis, building performance simulation, and city-scale dynamic demand response.

Unverified50%
Nov 16

The value of synthetic data ultimately depends on whether its deviation from the real world is controllable, and performance under cross-city generalization and extreme climate scenarios still requires more independent validation.

Unverified50%

All Facts (9)

Unverified

The DySENSE framework decouples urban problems into long-term stable urban form (static layer) and monthly energy consumption that fluctuates with seasonal climate (dynamic layer).

50%
Unverified

DySENSE supports two conditional generation settings: conditioned on static land use, generating realistic and spatially aligned satellite imagery and energy consumption maps; and conditioned on monthly and climate prompts, keeping urban form unchanged and jointly generating only dynamic monthly energy consumption maps.

50%
Unverified

DySENSE adopts multimodal joint generation, outputting multiple spatially aligned results (satellite imagery and energy consumption maps) in a single forward pass rather than staged serial generation.

50%
Unverified

The main technical difficulty of DySENSE is the inter-modality alignment constraint: building outlines in satellite imagery must be pixel-level consistent with high-value regions in energy consumption maps.

50%
Unverified

DySENSE was validated on four cities: New York, Washington, Norfolk, and Busan.

50%
Unverified

Using less than 25% of labeled data, DySENSE can generate labeled high-fidelity synthetic energy consumption data and improve downstream prediction performance by 8% mIoU.

50%
Unverified

Compared with existing methods, DySENSE improves prediction performance by 8.7% (accuracy) and reduces prediction error by 9%–18% (CVRMSE, ASHRAE standard).

50%
Unverified

DySENSE's application directions include energy-efficient urban planning, peak load analysis, building performance simulation, and city-scale dynamic demand response.

50%
Unverified

The value of synthetic data ultimately depends on whether its deviation from the real world is controllable, and performance under cross-city generalization and extreme climate scenarios still requires more independent validation.

50%

Source Articles