
黄河流域月尺度灌溉用水量的推算及其时空变化规律分析
王建辉, 冉金鑫, 沈莹莹, 韩振中, 崔远来, 罗玉峰
黄河流域月尺度灌溉用水量的推算及其时空变化规律分析
Estimation of Monthly Irrigation Water Consumption in the Yellow River Basin and Analysis of Its Temporal and Spatial Changes
获取准确的月尺度灌溉用水量对探究流域灌溉用水量时空变异规律具有重要意义。以黄河流域内24个灌溉分区为例,利用基于TensorFlow架构的BPNN来推算月尺度灌水量。收集了24个灌溉分区的作物类型、降雨、气象以及实测灌溉定额等数据对模型进行训练,验证了模型的精度,并对黄河流域2018年逐月灌溉用水量的时空变异规律进行了分析。结果表明:黄河流域内小麦和玉米的灌溉用水量最多,占总灌溉用水量的26.35%和37.98%,其余作物灌溉用水量按大小排序为蔬菜>油料>薯类>水稻>大豆>棉花;灌溉用水量呈现随着月份的变化先增加后减小的趋势,在6月份达到峰值;灌水量空间分布呈现从西北部至中部、再到东西部逐渐递减的趋势。
Obtaining accurate monthly irrigation water consumption is of great significance for exploring the temporal and spatial variation of the irrigation water consumption in a river basin. A BPNN based on the TensorFlow architecture is constructed to calculate the monthly irrigation volume taking a case study over 24 irrigation districts in the Yellow River Basin. The data of crop types, rainfall, weather, and measured irrigation quotas in 24 irrigation districts are collected to train the model, verify the accuracy of the model, and analyze the temporal and spatial variation of the monthly irrigation water consumption in the Yellow River Basin in 2018. The results show that the irrigation water consumption of wheat and corn in the Yellow River Basin is the largest, accounting for 26.35% and 37.98% of the total irrigation water consumption. The irrigation water consumption of other crops is in the order of vegetable>oil crops>potatoes>rice>soybean>cotton. Irrigation water consumption shows an increasing trend first and then a decreasing one over time, reaching a peak in June. The spatial distribution of irrigation water shows a trend of gradual decrease from the northwest to the middle, and then to the east and west.
月尺度灌水量 / 黄河流域 / TensorFlow / BP神经网络 / 灌水量推算 {{custom_keyword}} /
monthly irrigation volume / Yellow River Basin / TensorFlow / BP neural network / irrigation volume calculation {{custom_keyword}} /
表1 模型隐含层最优参数设定Tab.1 Optimal parameter setting of model hidden layer |
灌溉分区 | 作物类型 | 隐含层层数 | 隐含层节点数 | |
---|---|---|---|---|
第一层 | 第二层 | |||
陇中片 | 小麦 | 1 | 8 | - |
玉米 | 1 | 12 | - | |
薯类 | 1 | 10 | - | |
蔬菜 | 2 | 8 | 8 | |
温凉农业区 | 玉米 | 1 | 12 | - |
薯类 | 2 | 8 | 8 | |
蔬菜 | 1 | 10 | - | |
油料 | 1 | 12 | - | |
温暖半干旱农业区 | 水稻 | 1 | 12 | - |
北部引黄灌区 | 玉米 | 1 | 8 | - |
蔬菜 | 1 | 8 | 8 | |
中部干旱带 | 玉米 | 1 | 8 | - |
蔬菜 | 1 | 10 | - | |
南部山区库井灌区 | 玉米 | 1 | 8 | - |
蔬菜 | 1 | 10 | - | |
豫北平原区 | 小麦 | 2 | 8 | 10 |
玉米 | 1 | 10 | - | |
豫北山丘区 | 小麦 | 2 | 8 | 10 |
玉米 | 1 | 10 | - | |
豫西山丘区 | 小麦 | 2 | 10 | 10 |
玉米 | 1 | 8 | - | |
关中 | 小麦 | 1 | 8 | - |
玉米 | 1 | 6 | - | |
晋南区 | 小麦 | 2 | 10 | 10 |
玉米 | 1 | 12 | - |
表2 灌溉用水量仿真值与实测值对比Tab.2 Comparison between simulated and measured irrigation water consumption |
省(区) | 农田灌溉用水量/亿m3 | 相对误差绝对值/% | |
---|---|---|---|
实际值 | 仿真值 | ||
合计 | 226.98 | 220.28 | 2.96 |
内蒙古 | 66.27 | 69.84 | 5.39 |
宁夏 | 50.10 | 40.93 | 18.30 |
陕西 | 29.51 | 28.85 | 2.25 |
山西 | 27.23 | 31.83 | 16.91 |
河南 | 23.80 | 22.63 | 4.92 |
甘肃 | 22.00 | 18.51 | 15.77 |
青海 | 1.62 | 1.81 | 11.50 |
山东 | 6.46 | 5.86 | 9.28 |
1 |
谷红梅,张培雯,来和鑫,等.黄河流域农业节水绿色信用体系研究[J].节水灌溉,2021(6):53-57,63.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
2 |
张金萍,肖宏林.黄河流域灌区农业用水研究发展历程与展望[J].灌溉排水学报,2020,39(10):9-17.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
3 |
沈莹莹,张绍强,吉晔. 我国农业灌溉用水量统计方法的确定及工作开展情况[J]. 中国农村水利水电, 2016(11):133-133.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
4 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
5 |
刘小花,袁宏源,洪林,等. 水资源利用随机预测模型研究[J]. 中国农村水利水电, 2002(12):70-72.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
6 |
刘迪,胡彩虹,吴泽宁. 基于定额定量分析的农业用水需求预测研究[J]. 灌溉排水学报, 2008,27(6):88-91.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
7 |
常迪,齐学斌,黄仲冬. 区域农业灌溉用水量预测研究进展[J]. 中国农学通报, 2017,33(31):1-5.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
8 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
9 |
迟道才,唐延芳,顾拓,等.灌溉用水量的并联型灰色神经网络预测[J].农业工程学报,2009,25(5):26-29.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
10 |
刘玲,王丽珍,孙书洪,等.基于改进BP神经网络的农田灌溉用水量预测研究[J].灌溉排水学报,2015,34():197-199.
增刊1
{{custom_citation.content}}
{{custom_citation.annotation}}
|
11 |
王有恒,谭丹,韩兰英,等.黄河流域气候变化研究综述[J].中国沙漠,2021,41(4):235-246.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
12 |
陈龙. 甚低分辨率人脸幻构深度模型与算法研究[D]. 南京:南京邮电大学, 2019.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
13 |
林海宁. 应用Google Tensorflow的推荐系统[J]. 电脑知识与技术, 2018,14(28):195-196.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
14 |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_ref.label}} |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
/
〈 |
|
〉 |