add hydroevaluate

iHeadWater · May 30, 2024 · 279d3b0 · 279d3b0
1 parent 0d22e3d
commit 279d3b0
Show file tree

Hide file tree

Showing 8 changed files with 7 additions and 3 deletions.
diff --git a/README.md b/README.md
@@ -1,7 +1,7 @@
 <!--
  * @Author: Wenyu Ouyang
  * @Date: 2023-10-29 17:35:04
- * @LastEditTime: 2024-05-30 09:06:30
+ * @LastEditTime: 2024-05-30 09:09:18
  * @LastEditors: Wenyu Ouyang
  * @Description: Hydro forecast
  * @FilePath: \hydroevaluate\README.md
@@ -13,4 +13,6 @@ This project aims to provide a unified evaluation framework for hydrological mod
 
 Currently, both physically-based and machine learning-based hydrological models heavily rely on existing datasets for evaluation, without considering the performance of hydrological forecasts. For example, many papers divide the CAMELS dataset into training and testing sets, train models on the training set, and evaluate them on the testing set. However, in actual forecasting, it is common to distinguish between observed rainfall and forecasted rainfall. Models should not have access to any observed data within the forecast period. Therefore, a more realistic evaluation approach would be to evaluate models without using any observed data as input within the forecast period. While the differences may not be significant when comparing different models, this evaluation approach is more appropriate for assessing actual forecasting performance.
 
-Furthermore, there is a lot of research on model evaluation, and we will continuously incorporate relevant studies into the program to explore the topic more comprehensively.
+Furthermore, there is a lot of research on model evaluation, and we will continuously incorporate relevant studies into the program to explore the topic more comprehensively.
+
+**NOTE: this repo has just started.**
diff --git a/README_CN.md b/README_CN.md
@@ -1,7 +1,7 @@
 <!--
  * @Author: Wenyu Ouyang
  * @Date: 2024-02-12 09:52:49
- * @LastEditTime: 2024-05-30 09:05:20
+ * @LastEditTime: 2024-05-30 09:08:47
  * @LastEditors: Wenyu Ouyang
  * @Description: 中文版README
  * @FilePath: \hydroevaluate\README_CN.md
@@ -14,3 +14,5 @@
 现阶段不论是基于物理机制还是机器学习的水文模型，主要都依托于现成的数据集进行评估，并没有针对水文预报性能进行衡量。比如很多论文都会在CAMELS数据集上划分训练集、测试集，在训练集上训练的模型在测试集上评估，然而实际预报中，最典型的就是会区分落地雨和预报雨，模型在预见期内是不能有任何实际观测数据的，所以比较实际的评估方式应该是在预见期内不使用任何观测为输入的条件下进行评估。当然，从对比不同模型的角度来说，这其中的差别可能并不大，但是从实际预报性能的评估角度来说，这种评估方式是更加合理的。
 
 此外，关于模型评估的研究也很多，后续会不断补充进相关程序以更深入地探讨。
+
+**注：此项目刚刚启动**
diff --git a/...ts/aiff_config/GPM_GFS_Scaler_2_stat.json → hydroevaluate/GPM_GFS_Scaler_2_stat.json b/...ts/aiff_config/GPM_GFS_Scaler_2_stat.json → hydroevaluate/GPM_GFS_Scaler_2_stat.json
diff --git a/...process/results/aiff_config/aiff_v002.yml → hydroevaluate/aiff_v002.yml b/...process/results/aiff_config/aiff_v002.yml → hydroevaluate/aiff_v002.yml
diff --git a/scripts/postprocess/config.py → hydroevaluate/config.py b/scripts/postprocess/config.py → hydroevaluate/config.py
diff --git a/scripts/postprocess/eval_log.json → hydroevaluate/eval_log.json b/scripts/postprocess/eval_log.json → hydroevaluate/eval_log.json
diff --git a/scripts/postprocess/minio_api.py → hydroevaluate/minio_api.py b/scripts/postprocess/minio_api.py → hydroevaluate/minio_api.py
diff --git a/scripts/postprocess/model_stream.py → hydroevaluate/model_stream.py b/scripts/postprocess/model_stream.py → hydroevaluate/model_stream.py