GENERATING AN ABOVE GROUND BIOMASS PREDICTION MODEL
A method and apparatus of a device for generating an above ground biomass density prediction model is described. In an exemplary embodiment, the device receives a first set of satellite and optionally environmental data for the target landmass. In addition, the device trains an above ground biomass density model using at least the satellite data and Light Detection and Ranging (LIDAR) data. Furthermore, the device applies the above ground biomass density model using a second set of satellite and environmental biomass to generate the ground biomass density map.
1 . A non-transitory machine-readable medium having executable instructions to cause one or more processing units to perform a method of generating an above ground biomass density map of a target landmass, the method comprising:
receiving a first set of satellite and optionally environmental data for the target landmass;
training an above ground biomass density model using at least the satellite and Light Detection and Ranging (LIDAR) data; and
applying the above ground biomass density model using a second set of satellite and environmental data to generate the above ground biomass density map.
2 . The non-transitory machine-readable medium of claim 1 , wherein the method further comprises:
preprocessing the satellite data, wherein the preprocessed satellite data includes at least one of cloud masking data, shadow masking data, mosaicking data, and normalized difference spectral index calculation.
3 . The non-transitory machine-readable medium of claim 2 , wherein the method further comprises:
generating a normalized difference spectral index stack from the preprocessed satellite data.
4 . The non-transitory machine-readable medium of claim 1 , wherein the satellite imagery data includes at least one of multispectral satellite data and synthetic-aperture radar imagery data.
5 . The non-transitory machine-readable medium of claim 1 , wherein the LIDAR data includes global ecosystem dynamics investigation LIDAR data.
6 . The non-transitory machine-readable medium of claim 1 , wherein the environmental data includes climate data.
7 . The non-transitory machine-readable medium of claim 1 , wherein the environmental data includes land cover data.
8 . The non-transitory machine-readable medium of claim 1 , wherein the environmental data includes digital elevation model data.
9 . The non-transitory machine-readable medium of claim 8 , further comprising:
preprocessing the digital elevation model data; and
generating a digital elevation model stack from the preprocessed digital elevation model data.
10 . The non-transitory machine-readable medium of claim 1 , wherein the method further comprises:
receiving training data for the above ground biomass density model, wherein the training data includes at least one of satellite data and environmental data;
training the above ground biomass density model using light gradient boosted machine learning algorithm; and
outputting the above ground biomass density prediction model.
11 . The non-transitory machine-readable medium of claim 10 , wherein the method further comprises:
generating an above ground biomass density map using the above ground biomass density prediction model.
12 . The non-transitory machine-readable medium of claim 10 , wherein the training further includes using Bayesian optimization.
13 . A method of generating an above ground biomass density map of a target landmass, the method comprising:
receiving a first set of satellite and optionally environmental data for the target landmass;
training an above ground biomass density model using at least the satellite and Light Detection and Ranging (LIDAR) data; and
applying the above ground biomass density model using a second set of satellite and environmental data to generate the above ground biomass density map.
14 . The method of claim 13 , wherein the method further comprises:
preprocessing the satellite data, wherein the preprocessed satellite data includes at least one of cloud masking data, shadow masking data, mosaicking data, and normalized difference spectral index calculation.
15 . The method of claim 14 , wherein the method further comprises:
generating a normalized difference spectral index stack from the preprocessed satellite data.
16 . The method of claim 13 , wherein the satellite imagery data includes at least one of multispectral satellite data and synthetic-aperture radar imagery data.
17 . The method of claim 13 , wherein the LIDAR data includes global ecosystem dynamics investigation LIDAR data.
18 . The method of claim 13 , wherein the environmental data includes climate data.
19 . The method of claim 13 , wherein the environmental data includes land cover data.
20 . The method of claim 13 , wherein the environmental data includes digital elevation model data.