DSD-INT 2018 Data-driven impact modelling for the estimation of disaster damage - Wagenaar
Data-driven impact modelling
Data-driven impact modelling for the estimation of disaster damage
• Decision making for disaster prevention,
response and recovery.
• Disaster impacts are typically what
determines how to respond and what
measures are feasible .
• Possible disaster impacts:
• Flood damage
• Flood casualties
• People affected
• Required assistance
• Required building materials
Why model disaster impacts
Application of impact modelling
• CBA infrastructure investments
• Risk screening studies
• Adaptive delta management
• Setting insurance premiums
• Climate change impact
• How much money is needed
• Allocation of recovery funds
Impact Based Forecasting:
Warning information and
Prioritization of rescue and aid
Current approach: Types of disaster damage
Category Tangible Intangible
Direct • Capital (buildings incl.
contents, crops, cars)
• Production losses, income
• Casualties, injuries,
• Social disruption, emotional
Indirect • Production losses / loss of
utility services outside
• Unemployment, migration.
• Cutting of infrastructure
• Loss of potential for attracting
• Reputation damage
Delft-FIAT Multiplication factor
5-100% of capital damage
Current approach: Delft-FIAT
Vulnerability: The damage function
• Expert or group of experts come together
and estimate a damage function.
• Elements of object of interest can be
• Weakness: experts typically have one
setting in mind.
Data-driven approach (empirical)
• Regression analysis on available data
points of past flood damage.
• Weakness: Data availability and bad
Things not to do with current approach:
• Copy damage functions from the literature (transfer)
• CBA for measures that influence anything but water depth
and probability (e.g. resilience measures)
• Allocation of recovery funds
• Detailed prioritization of emergency help
• Uncertainty estimation (for insurance premiums)
Gaps in current approach
• Large differences in damage functions (hidden assumptions)
The multi-variable data-driven approach
From: Damage fraction = f(water depth)
To: Damage fraction = f(water depth, warning time, wave height, …..)
DF = f(water depth) DF = f(water depth, warning time, waves height, …..)
Multi-variable damage models can be build from data with Machine
• Multi-variable linear regression
• Tree methods
• Regression trees
• Bagging trees
• Random Forest
• Artificial Neural Networks
• Bayesian Networks
• Support Vector Machines
Supervised Machine Learning methods
Example with limited number of dimensions
Required data and supervised Machine Learning
depth velocity duration warning population …. damage
1.3 0.25 190 3 4…. €32,000
2.1 0.15 250 5 2… €21,000
…. ….. ….. ….. …. … ….
1.8 0.2 160 4 3… ?
variableFeatures / independent variables / characteristics
• We found out that in some cases multi-variable flood damage models
can be transferred.
• Transfer from Germany to Netherlands worked well
• Transfer from Netherlands to Germany went wrong
• We are working on techniques to make this transfer work better
We need more data!
• Purpose to find relationships between
features and damage.
• We only need samples!
• Good heterogeneous samples better
than large amount.
• Definitions and collection guidelines.
• Collection probably manual labor?
• Global organization to coordinate
• Purpose data required for model
• Needs to be complete for study area.
• Collection using remote sensing
• Need good hazard models
• Can sometimes be estimated
Building feature recognition