1.-Data-Processing.md

@@ -7,7 +7,8 @@ Locations for model training on 4 locations
 - (35.1667, 33.3667),   # Nicosia, Cyprus
 - (59.3293, 18.0686),   # Stockholm, Sweden
 
-![4loc](uploads/23ca0c708ca48dfeb6d8e0919428a037/4loc.png)
+![Selection_044](uploads/cacc195254a5ac32bd91b2f2d7543d80/Selection_044.png)
+
 
 Additional locations for model training on all locations, with variety of temperate ranges
 
@@ -38,24 +39,15 @@ Additional locations for model training on all locations, with variety of temper
 
 Location for model validation
 
-- (59.3293, 18.0686),    # Stockholm, Sweden
+- (62.2426, 25.7473),   # Jyväskylä, Finland
 - (38.7223, -9.1393),    # Lisbon, Portugal
 - (50.4501, 30.5234),    # Kyiv, Ukraine
-- (37.9838, 23.7275),    # Athens, Greece
-- (48.2082, 16.3738),    # Vienna, Austria
-- (53.3498, -6.2603),    # Dublin, Ireland
-- (35.8989, 14.5146),    # Valletta, Malta
-- (78.2232, 15.6469),    # Svalbard, Norway
-- (69.9058, 27.0287),    # Utsjoki, Finland
-- (37.3891, -5.9845),    # Seville, Spain
-- (37.5079, 15.0830)     # Catania, Sicily, Italy
-
-![lat_lons_map](uploads/37d7f12f798fcfe8195e98609073cd4d/lat_lons_map.png)
-
-Additional stand-alone location for validation
-
-- (48.1351, 11.5820)     # Germany, Munich
+- (38.1157, 13.3615),    # Palermo, Sicily, Italy
+- (38.4237, 27.1428),   # Izmir, Turkey
+- (51.0504, 13.7373),   # Dresden, Germany
+- (55.9533, -3.1883)   # Edinburgh, United Kingdom
 
+![Selection_045](uploads/70257aa2eb514a9cd30d872f47bbdc32/Selection_045.png)
 
 **Data source and inspection**
 
@@ -142,7 +134,7 @@ After separating time index and feature engineering the dataframe consists of th
 **Data Model-Preparation**
 Afterwards I normalize and scale the data with a MinMaxScaler.
 
-With this code the sequences with sequence length = 6 and param = 'T2M' for the model are created.
+With this code the sequences with sequence length = 6 and param = 'T2M' for the model are created. 80:20 is the ratio of the training data and test data per dataset in all_data
 ```
     X_train, y_train = [], []
     for i in range(len(train_df) - sequence_length - hours_to_predict + 1):