Update README.md
Browse files
README.md
CHANGED
@@ -140,23 +140,22 @@ validation period.
|
|
140 |
### Preprocessing
|
141 |
|
142 |
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.
|
143 |
-
This section defines the preprocessing steps undertaken to homogenize these datasets into a common format.
|
144 |
-
The
|
145 |
-
The rationale and methodologies employed in each step are discussed comprehensively, setting a robust foundation for the subsequent training procedure.
|
146 |
|
147 |
-
|
148 |
-
This was imperative to ensure a uniform unit system, facilitating a seamless integration of the datasets in later stages.
|
149 |
-
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.
|
150 |
|
151 |
-
|
152 |
-
Specifically, the coordinates and dimensions were renamed to a standardized format with longitude (lon) and latitude (lat) as designated names.
|
153 |
-
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,
|
154 |
thereby aligning with conventional geographical coordinate systems.
|
155 |
|
156 |
-
|
157 |
-
|
158 |
-
This step
|
159 |
-
The interpolation transformed the CERRA dataset to match the regular grid structure of the ERA5 dataset, keeping its initial spatial resolution
|
|
|
160 |
|
161 |
### Speeds, Sizes, Times
|
162 |
|
|
|
140 |
### Preprocessing
|
141 |
|
142 |
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.
|
143 |
+
This section defines the preprocessing steps undertaken to homogenize these datasets into a common format. The steps include unit standardization, coordinate system
|
144 |
+
rectification, and grid interpolation. The methodology employed in each step is discussed comprehensively in the following paragraphs:
|
|
|
145 |
|
146 |
+
- Unit Standardization: A preliminary step in the preprocessing pipeline involved the standardization of units across both datasets.
|
147 |
+
This was imperative to ensure a uniform unit system, facilitating a seamless integration of the datasets in later stages.
|
|
|
148 |
|
149 |
+
- Coordinate System Rectification: The coordinate system of the datasets was rectified to ensure a coherent representation of geographical information.
|
150 |
+
Specifically, the coordinates and dimensions were renamed to a standardized format with longitude (lon) and latitude (lat) as designated names.
|
151 |
+
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,
|
152 |
thereby aligning with conventional geographical coordinate systems.
|
153 |
|
154 |
+
- Grid Interpolation: 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
|
155 |
+
a Lambert Conformal projection of higher spatial resolution (0.05º). To overcome this disparity in the grid system, a grid interpolation procedure is performed.
|
156 |
+
This step is crucial to align the datasets onto a common format, a regular grid (with different spatial resolutions), thereby ensuring consistency in spatial
|
157 |
+
representation. The interpolation transformed the CERRA dataset to match the regular grid structure of the ERA5 dataset, keeping its initial spatial resolution
|
158 |
+
of 0.05º (5.5 km).
|
159 |
|
160 |
### Speeds, Sizes, Times
|
161 |
|