Frederik Kratzert

Johannes Kepler University, Linz, Austria

 Recent Activity

ABSTRACT:

This repository contains drop-in replacements for the basin mean NLDAS forcing data files of the CAMELS data set. Compared to the original files contained in the CAMELS data set, these files contain daily minimum and maximum temperature. In the original publications both of those variables contained the daily mean temperature. These files were generated for our HESS manuscript "Toward Improved Predictions in Ungauged Basins: Exploiting the Power of Machine Learning" and were derived from hourly NLDAS data.
The same TERMS OF USE apply as for the original CAMELS data set.
The same terms of use as of the original CAMELS data set apply here.

Show More

ABSTRACT:

Contains all models trained for our publication "Towards learning universal, regional, and local hydrological behaviors via machine learning applied to large-sample datasets", as well as the evaluated model simulations. The set contains 48 runs in total, stemming from 3 different models (trained with 8 repetitions) and two different loss functions.

Show More

ABSTRACT:

This repository contains drop-in replacements for the basin mean Maurer forcing data files of the CAMELS data set. Compared to the original files contained in the CAMELS data set, these files contain daily minimum and maximum temperature. In the original publications both of those variables contained the daily mean temperature. These files were generated for our HESS manuscript "Towards learning universal, regional, and local hydrological behaviors via machine learning applied to large-sample datasets" and will be merged into the official CAMELS data set in the next update.
The same TERMS OF USE apply as for the original CAMELS data set.

Show More

ABSTRACT:

This data set contains the model outputs of different hydrology models calibrated using the same forcing data (Maurer) and the same calibration period for the CAMELS data set. The models are: SAC-SMA, VIC, HBV, FUSE and mHM. All of these models have been calibrated for each basin separately. Additionally, for VIC and mHM, also regionally calibrated model outputs exist. All models have been calibrated using the period 1 October 1999 until 30 September 2008 and were validated in the period 1 October 1989 until 30 September 1999.

Show More

 Contact

Resources
All 0
Collection 0
Resource 0
App Connector 0
Resource Resource
CAMELS benchmark models
Created: July 9, 2019, 11:30 a.m.
Authors: Kratzert, Frederik

ABSTRACT:

This data set contains the model outputs of different hydrology models calibrated using the same forcing data (Maurer) and the same calibration period for the CAMELS data set. The models are: SAC-SMA, VIC, HBV, FUSE and mHM. All of these models have been calibrated for each basin separately. Additionally, for VIC and mHM, also regionally calibrated model outputs exist. All models have been calibrated using the period 1 October 1999 until 30 September 2008 and were validated in the period 1 October 1989 until 30 September 1999.

Show More
Resource Resource
CAMELS Extended Maurer Forcing Data
Created: July 18, 2019, 11:15 a.m.
Authors: Kratzert, Frederik

ABSTRACT:

This repository contains drop-in replacements for the basin mean Maurer forcing data files of the CAMELS data set. Compared to the original files contained in the CAMELS data set, these files contain daily minimum and maximum temperature. In the original publications both of those variables contained the daily mean temperature. These files were generated for our HESS manuscript "Towards learning universal, regional, and local hydrological behaviors via machine learning applied to large-sample datasets" and will be merged into the official CAMELS data set in the next update.
The same TERMS OF USE apply as for the original CAMELS data set.

Show More
Resource Resource

ABSTRACT:

Contains all models trained for our publication "Towards learning universal, regional, and local hydrological behaviors via machine learning applied to large-sample datasets", as well as the evaluated model simulations. The set contains 48 runs in total, stemming from 3 different models (trained with 8 repetitions) and two different loss functions.

Show More
Resource Resource
CAMELS Extended NLDAS Forcing Data
Created: Dec. 24, 2019, 12:51 p.m.
Authors: Kratzert, Frederik

ABSTRACT:

This repository contains drop-in replacements for the basin mean NLDAS forcing data files of the CAMELS data set. Compared to the original files contained in the CAMELS data set, these files contain daily minimum and maximum temperature. In the original publications both of those variables contained the daily mean temperature. These files were generated for our HESS manuscript "Toward Improved Predictions in Ungauged Basins: Exploiting the Power of Machine Learning" and were derived from hourly NLDAS data.
The same TERMS OF USE apply as for the original CAMELS data set.
The same terms of use as of the original CAMELS data set apply here.

Show More