Update README.md
Browse filesAdding processing steps to the data downloaded from the CDS
README.md
CHANGED
@@ -136,7 +136,27 @@ The data samples used for training corresponds to the period from 1985 and 2013
|
|
136 |
|
137 |
### Preprocessing
|
138 |
|
139 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
140 |
|
141 |
### Speeds, Sizes, Times
|
142 |
|
|
|
136 |
|
137 |
### Preprocessing
|
138 |
|
139 |
+
The preprocessing of climate datasets ERA5 and CERRA, extracted from the Climate Data Store (CDS), is a critical step before their utilization in training models.
|
140 |
+
This paper delineates the series of preprocessing steps undertaken to homogenize these datasets into a common format conducive for the ensuing experiment. The steps
|
141 |
+
include unit standardization, coordinate system rectification, and grid interpolation. The rationale and methodologies employed in each step are discussed comprehensively,
|
142 |
+
setting a robust foundation for the subsequent training procedure.
|
143 |
+
|
144 |
+
1. Unit Standardization:
|
145 |
+
A preliminary step in the preprocessing pipeline involved the standardization of units across both datasets.
|
146 |
+
This was imperative to ensure a uniform unit system, facilitating a seamless integration of the datasets in later stages.
|
147 |
+
The units in both datasets were scrutinized and amended to adhere to a common unit system, thereby eliminating any discrepancies that could hinder the analysis.
|
148 |
+
|
149 |
+
2. Coordinate System Rectification:
|
150 |
+
The coordinate system of the datasets was rectified to ensure a coherent representation of geographical information.
|
151 |
+
Specifically, the coordinates and dimensions were renamed to a standardized format with longitude (lon) and latitude (lat) as designated names.
|
152 |
+
The longitude values were adjusted to range from -180 to 180 instead of the initial 0 to 360 range, while latitude values were ordered in ascending order,
|
153 |
+
thereby aligning with conventional geographical coordinate systems.
|
154 |
+
|
155 |
+
3. Grid Interpolation:
|
156 |
+
The ERA5 dataset is structured on a regular grid with a spatial resolution of 0.25º, whereas the CERRA dataset inhabits a curvilinear grid with a Lambert Conformal
|
157 |
+
projection of higher spatial resolution (0.05º). To overcome this disparity, a grid interpolation procedure was initiated.
|
158 |
+
This step was crucial to align the datasets onto a common regular grid (with different spatial resolution), thereby ensuring consistency in spatial representation.
|
159 |
+
The interpolation transformed the CERRA dataset to match the regular grid structure of the ERA5 dataset, thus harmonizing the spatial resolution across both datasets.
|
160 |
|
161 |
### Speeds, Sizes, Times
|
162 |
|