ouyangwenyu / hydromodel Goto Github PK
View Code? Open in Web Editor NEW新安江水文模型
License: GNU General Public License v3.0
新安江水文模型
License: GNU General Public License v3.0
暂时解决,感谢!
我想问一下关于数据camels_us用于新安江率定的参数初始值是多少?从哪个文件看呢
用pycharm运行calibrate_xaj.py时提示出现该问题,但是所有包都安装完毕,也没有修改程序。请教是什么原因
Please add documentation
我发现模型里面没有用到二维数据,比如代表地形的dem数据,代表流域边界的shp数据等。模型中没有用到这些数据吗
在运行test.py 的时候程序报错:没有hydroeval 和 platypus 模块 。 请问这两个是什么库?
在终端中pip install 对应的库过后,任然找不到对应的子模块
作者您好,可以大概给介绍一下代码当中用于训练的数据的构成么?感激不尽!
您好,我使用仓库中的样例数据运行了 hydromodel.models.xaj 方法,返回值q_sim是一个数组。他代表的是什么意思呢,是每个网格的预测流量吗
Ouyang你好,我目前也从事新安江水文模型的相关研究,有幸学习到您的代码。在研读wiki中实测径流分析模块时,发现缺少退水曲线和洪水分割这两部分的代码。而我自身编程水平有限,还在学习作者的思路中,因此想请问作者什么时候更新这部分的code,或者我们可以交流探讨一下。
Traceback (most recent call last):
File "G:\yanling\bysj\xinanj\hydro-model-xaj-master\hydro-model-xaj-master\hydromodel\data\data_postprocess.py", line 263, in
read_and_save_et_ouputs(one_model_one_hyperparam_setting_dir, fold=0)
File "G:\yanling\bysj\xinanj\hydro-model-xaj-master\hydro-model-xaj-master\hydromodel\data\data_postprocess.py", line 226, in read_and_save_et_ouputs
_, e_train = xaj(
File "G:\yanling\bysj\xinanj\hydro-model-xaj-master\hydro-model-xaj-master\hydromodel\models\xaj.py", line 785, in xaj
_q, _e, *w0, s0, fr0, qi0, qg0 = xaj(
File "G:\yanling\bysj\xinanj\hydro-model-xaj-master\hydro-model-xaj-master\hydromodel\models\xaj.py", line 808, in xaj
(r, rim, e, pe), w = generation(
File "G:\yanling\bysj\xinanj\hydro-model-xaj-master\hydro-model-xaj-master\hydromodel\models\xaj.py", line 222, in generation
eu, el, ed = calculate_evap(lm, c, wu0, wl0, prcp, pet)
File "D:\miniconda\envs\xaj\lib\site-packages\numba\np\arraymath.py", line 3481, in where_impl
raise ValueError("all inputs should have the same shape")
ValueError: all inputs should have the same shape
Process finished with exit code 1
你好,我看示例数据中时段是天为单位的,我想问下如果我想跑3h时段长的数据是否需要修改些内容?我制作输入文件试了下是可以跑通,但是不太确定计算是否可以直接用于小时时段的,参数需要处理下吗?
Please Check your directory:
ROOT_DIR of the repo: D:\hydro-model-xaj-master\hydro-model-xaj-master
DATASET_DIR of the repo: D:\data
Compare evaluation results of different calibrated models in an exp directory
All settings in an exp directory: 0it [00:00, ?it/s]
Traceback (most recent call last):
File "datapostprocess4calibrate.py", line 156, in
statistics(the_args)
File "datapostprocess4calibrate.py", line 112, in statistics
mean_df_test = pd.concat(mean_lst_test, axis=1).T
File "D:\ProgramData\Anaconda3\envs\xaj\lib\site-packages\pandas\util_decorators.py", line 311, in wrapper
return func(*args, **kwargs)
File "D:\ProgramData\Anaconda3\envs\xaj\lib\site-packages\pandas\core\reshape\concat.py", line 304, in concat
sort=sort,
File "D:\ProgramData\Anaconda3\envs\xaj\lib\site-packages\pandas\core\reshape\concat.py", line 351, in init
raise ValueError("No objects to concatenate")
ValueError: No objects to concatenate
你好,我看到您的example中给出的训练集测试集中他们是将4个流域的数据放到一起,并且他们有着相同的时间长度,我现在想要使用自己的数据集进行训练,我的数据是一个流域的多个场次洪水,他们不是连续的时间序列,那么我该如何进行处理
水平有限,还没跑起来。wiki里面对模型原理的讲解非常详细,有很多探究和思考。比较惊叹贡献者的知识体系和数学功底。
我看到readme文件中提到模型的数据是一个三维数组[时间,流域,变量]。那这里的变量是指什么,我看到代码中变量应该是降雨和蒸散发数据,对吗。
换句话说,预报模型中,需要降雨数据/蒸散发数据和率定出来的16个变量这三类数据对吗。
Appreciate for your work.Here I have some questions. Are the parameters "a and theta" just same as "n and k"? If not ,how to convert?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.