LSTM模型在耕地面积预测领域的构建与应用

doi:10.3981/j.issn.1000-7857.2021.09.012

Abstract
Figure/Table
References (0)
Related Citation (15)

Download: PDF (1217 KB) HTML^new
Export: BibTeX | EndNote (RIS)

Abstract: The long-short term memory model (LSTM) is a special recurrent neural network structure, which is widely used in system failure, traffic flow, stock index, emergency event, carbon emission, water table depth, and other fields, showing excellent prediction performance. This paper introduces the LSTM model into forecasting cultivated land area to enrich predicting methods and improve prediction accuracy. To verify the validity of the LSTM model in cultivated land area prediction, TE, GM, ES, ARIMA, SVM and NARNET models are selected for comparison, in which Heilongjiang, Jilin and Liaoning provinces are taken as case areas for revealing evaluation effects of different time series models. The results indicate that the prediction effect of LSTM is better than other models in terms of the comprehensive evaluation of RMSE and MAPE. Finally, according to LSTM forecast, the cultivated land areas of Heilongjiang, Jilin and Liaoning provinces will continue to decrease from 2018 to 2030 and the decrease rate will slow down.

Key words： cultivated land forecast model deep learning neural network LSTM

Received: 20 August 2020

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	XIANG Yan
	HOU Yanlin
	JIANG Wenlai
	CHEN Yinjun
	CHENG Liangqiang

Cite this article:

XIANG Yan,HOU Yanlin,JIANG Wenlai, et al. Establishment and application of LSTM model for cultivated land area prediction[J]. Science & Technology Review, 2021, 39(9): 100-108.

URL:

http://www.kjdb.org/EN/10.3981/j.issn.1000-7857.2021.09.012 OR http://www.kjdb.org/EN/Y2021/V39/I9/100

[1] 封志明, 刘宝勤, 杨艳昭. 中国耕地资源数量变化的趋势分析与数据重建:1949~2003[J]. 自然资源学报, 2005(1):35-43.
[2] 汪涌, 王滨, 马仓, 等. 基于耕地面积订正的中国复种指数研究[J]. 中国土地科学, 2008, 22(12):46-52.
[3] 陈印军, 易小燕, 方琳娜, 等. 中国耕地资源与粮食增产潜力分析[J]. 中国农业科学, 2016, 49(6):1117-1131.
[4] 张琳, 张凤荣, 薛永森, 等. 中国各省耕地数量占补平衡趋势预测[J]. 资源科学, 2007, 29(6):114-119.
[5] 季翔, 刘黎明, 起晓星. 区域耕地粮食生产保障能力及其风险评价方法[J]. 农业工程学报, 2014, 30(7):219-226.
[6] 谢树春, 朱建军, 宋永永. 基于粮食安全的宁夏耕地需求量预测[J]. 农业现代化研究, 2016, 37(4):663-670.
[7] 张豪, 罗亦泳, 张立亭, 等. 基于遗传算法最小二乘支持向量机的耕地变化预测[J]. 农业工程学报, 2009, 25(7):226-231.
[8] 王霞, 王占岐, 金贵, 等. 基于核函数支持向量回归机的耕地面积预测[J]. 农业工程学报, 2014, 30(4):204-211.
[9] 罗亦泳, 张豪, 张立亭. 基于自适应进化相关向量机的耕地面积预测模型[J]. 农业工程学报, 2015, 31(9):257-264.
[10] 车明亮, 聂宜民, 刘登民, 等. 区域耕地数量变化预测方法的对比研究[J]. 中国土地科学, 2010, 24(5):13-18.
[11] 王全喜, 孙鹏举, 刘学录, 等. 基于随机森林算法的耕地面积预测及影响因素重要性分析——以甘肃省庆阳市为例[J]. 水土保持通报, 2018, 38(5):341-346.
[12] 王鑫, 吴际, 刘超, 等. 基于LSTM循环神经网络的故障时间序列预测[J]. 北京航空航天大学学报, 2018, 44(4):772-784.
[13] 王祥雪, 许伦辉. 基于深度学习的短时交通流预测研究[J]. 交通运输系统工程与信息, 2018, 18(1):81-88.
[14] 杨青, 王晨蔚. 基于深度学习LSTM神经网络的全球股票指数预测研究[J]. 统计研究, 2019, 36(3):65-77.
[15] Cortez B, Carrera B, Kim Y J, et al. An architecture for emergency event prediction using LSTM recurrent neural networks[J]. Expert Systems with Applications, 2018, 97:315-324.
[16] Huang Y S, Shen L, Liu H. Grey relational analysis, principal component analysis and forecasting of carbon emissions based on long short-term memory in China[J]. Journal of Cleaner Production, 2019, 209:415-423.
[17] Sagheer A, Kotb M. Time series forecasting of petroleum production using deep LSTM recurrent networks[J]. Neurocomputing, 2018, 323:203-213.
[18] Zhanga J, Zhub Y, Zhanga X, et al. Developing a Long Short-Term Memory (LSTM) based model for predicting water table depth in agricultural areas[J]. Journal of Hydrology, 2018, doi:10.1016/j.jhydrol.2018.04.065.
[19] 国土资源部, 国家统计局, 全国农业普查办公室. 关于土地利用现状调查主要数据成果的公报[J]. 中国统计, 1999(12):5, 14.
[20] 蔡运龙, 汪涌, 李玉平. 中国耕地供需变化规律研究[J]. 中国土地科学, 2009, 23(3):11-18, 31.
[21] 宋小青, 吴志峰, 欧阳竹. 1949年以来中国耕地功能变化[J]. 地理学报, 2014, 69(4):435-447.
[22] 金涛. 中国粮食作物种植结构调整及其水土资源利用效应[J]. 自然资源学报, 2019, 34(1):14-25.
[23] 郑亚楠, 张凤荣, 谢臻, 等. 中国粮食生产时空演变规律与耕地可持续利用研究[J]. 世界地理研究, 2019, 28(6):120-131.
[24] Hochreiter S, Schmidhuber, J. Long Short-Term Memory[J]. Neural Computation, 1997, 9(8):1735-1780.
[25] Graves A. Supervised Sequence Labelling with Recurrent Neural Networks[J]. Berlin Heidelberg:Springer, 2012:5-13.
[26] 周瑞, 魏正英, 张育斌, 等. 基于LSTM递归神经网络的番茄目标产量时间序列预测[J]. 节水灌溉, 2018(8):66-70.
[27] 陈威, 祁伟彦, 袁福香, 等. 基于时间序列与横截面数据的吉林省水稻产量预测对比分析[J]. 中国农业信息, 2018, 30(5):95-105.
[28] 刘炳春, 齐鑫, 王庆山. 北京城市代谢预测研究——基于长短期记忆神经网络模型[J]. 地理科学进展, 2019, 38(6):851-860.