/JDS_ML

machine learning to predict measurements in the Joint Danube Survey (JDS)

Primary LanguageJupyter NotebookMIT LicenseMIT

README -

Description of data locations

Hydro - JDS_ML\hydrology\sc_outflows.his

Connectivity - \JDS_ML\hydrology\NewHypeSchematisation.xlsx columns SUBID & HAROID Haroid is sub id, 9600704 is the value for danube catchment "Maindown" is the downstream subcatchment "Uparea" is cummulative upstream area Note that elev and slop info exists

Raw geodata is \JDS_ML\hydrology\GeoData.txt, with SLC SLC (landcover) characteristics: \JDS_ML\hydrology\GeoClass.txt

JDS stations with respect to subcatchment JDS_ML\measurements\JDSStat.prn also see locators tab in JDS_ML\geography\copy_locators_hypefinal_Nov2017.xlsx

Emissions for pesticides JDS_ML\emissions\prepare_for_ESpace_pesticides_v2.xlsx

see emissions for SOLUTIONS tab

Emissions for pharmaceuticals JDS_ML\emissions\prepare_for_ESpace_pharmaceuticals_v3.xlsx Tab EmisData

Emissions for reach JDS_ML\emissions\prepare_for_ESpace_REACH_v2.xlsx

Example emissions per country p:\1209104-solutions\WP14\SIM_Prod\EN_Europe_validation\Subout\espaceCAS_100-41-4.dbg, COULD BE *.MES