光温因子驱动的园艺作物叶龄模型模拟精度比较

doi:10.3969/j.issn.1004-1524.20231311

浙江农业学报 ›› 2024, Vol. 36 ›› Issue (6): 1368-1378.DOI: 10.3969/j.issn.1004-1524.20231311

光温因子驱动的园艺作物叶龄模型模拟精度比较

程陈¹^,²(), 董朝阳³, 郑生宏⁴, 周宇博¹, 钟宁¹, 李文明⁵, 朱阳春¹, 丁枫华¹, 冯利平², 黎贞发³^,^*()

1.丽水学院生态学院,浙江丽水 323000
2.中国农业大学资源与环境学院,北京 100193
3.天津市气候中心,天津 300074
4.丽水市农林科学研究院茶叶研究所,浙江丽水 323000
5.丽水市气象局,浙江丽水 323050

收稿日期:2023-11-20 出版日期:2024-06-25 发布日期:2024-07-02
作者简介:程陈(1993—),男,安徽合肥人,博士,讲师,从事作物模型与环境调控、专家决策系统开发与应用研究。E-mail:chengsir1993@lsu.edu.cn
通讯作者: *黎贞发,E-mail:lzfaaa@126.com
基金资助:
浙江省软科学研究计划项目(2022C35063);天津市蔬菜产业技术体系创新团队科研专项(201716);丽水市“百名博士入百家企业人才引领计划”项目(2022002);丽水学院人才启动基金项目(6604CC01Z);浙江省大学生科技创新活动计划(新苗人才计划)项目(2022 R434C021);浙江省大学生科技创新活动计划(新苗人才计划)项目(2023R480014);浙江省大学生科技创新活动计划(新苗人才计划)项目(2023R480021);国家级大学生创新创业训练计划(S202210352001X);国家级大学生创新创业训练计划(S202210352009);国家级大学生创新创业训练计划(S202210352010)

Comparison of simulation accuracy of leaf age models for horticultural crops driven by light and temperature factors

CHENG Chen¹^,²(), DONG Chaoyang³, ZHENG Shenghong⁴, ZHOU Yubo¹, ZHONG Ning¹, LI Wenming⁵, ZHU Yangchun¹, DING Fenghua¹, FENG Liping², LI Zhenfa³^,^*()

1. College of Ecology, Lishui University, Lishui 323000, Zhejiang, China
2. College of Resources and Environment Sciences, China Agricultural University, Beijing 100193, China
3. Tianjin Climate Centre, Tianjin 300074, China
4. Tea Research Institute, Lishui Academy of Agricultural and Forestry Sciences, Lishui 323000, Zhejiang, China
5. Lishui Meteorological Bureau, Lishui 323050, Zhejiang, China

Received:2023-11-20 Online:2024-06-25 Published:2024-07-02

摘要/Abstract

摘要：

为了提高光温因子驱动的园艺作物通用性叶龄模拟模型的模拟精度,以黄瓜、芹菜、菠菜、小香芹、郁金香和茶叶为供试材料,进行了7年(2016—2022年)的分期播种试验,依据作物生长发育与关键气象因子(辐射和温度)的关系,采用4类建模方法(温差法、积温法、生理发育时间法和辐热积法)构建了园艺作物叶龄模拟模型,并以6种方式(平均值、最值均值、中值、逐步回归、BP神经网络和Elman神经网络)和2种集成逻辑(直接和分步)集成模拟结果,最终优化模型模拟精度。结果表明:1)2种集成逻辑下模型模拟精度均较高,且分步集成逻辑优于直接集成逻辑,平均绝对误差(mean absolute error, MAE)差值为0.31 d,平均相对误差(mean relative error, MRE)差值为0.33%,均方根误差(root mean square error, RMSE)差值为0.40 d,归一化均方根误差(normalized root mean square error, NRMSE)差值为0.46%;2)2种集成逻辑下模型最优时间尺度为逐时尺度,最优作物类型为茶叶,最优建模方法为Elman神经网络集成模拟模型。研究结果可为园艺作物智慧生产管理和可视化提供理论依据和技术支撑。

关键词: 园艺作物, 叶龄模型, 逐步回归, 神经网络, 算法集成逻辑

Abstract:

The purpose of this study was to improve the simulation accuracy of a universal leaf age model driven by light-temperature factors for horticultural crops. In order to achieve this, cucumber, celery, spinach, coriander, tulip, and tea were selected as experimental materials and 7 years (2016-2022) staged sowing experiment was conducted. Based on the relationship between crop growth and key weather factors (radiation and temperature), 4 modeling methods (accumulated temperature difference method, accumulated temperature method, physiological development time method, and accumulated product of thermal effectiveness and photosynthetically active radiation method), 6 approaches (mean value, mean of extreme values, median, stepwise regression, BP neural network, and Elman neural network) and 2 integration logics (direct and stepwise) were employed to integrate the simulation results, aiming to optimize the accuracy of the model used to construct the leaf age simulation model for horticultural crops. Results showed that: 1) The models under both integration logics exhibited high simulation accuracy, with the stepwise integration logic performing better than the direct integration logic. The differences in mean absolute error (MAE), mean relative error (MRE), root mean square error (RMSE), and normalized root mean square error (NRMSE) were 0.31 d, 0.33%, 0.40 d, and 0.46% respectively. 2) The optimal time scale for the models under both integration logics was hourly, while tea was the optimal crop type, and the Elman neural network integration simulation model was the optimal modeling method. The findings of this study can provide theoretical basis and technical support for intelligent production management and visualization of horticultural crops.

Key words: horticultural crops, leaf age model, stepwise regression, neural networks, algorithmic integration logic

中图分类号:

程陈, 董朝阳, 郑生宏, 周宇博, 钟宁, 李文明, 朱阳春, 丁枫华, 冯利平, 黎贞发. 光温因子驱动的园艺作物叶龄模型模拟精度比较[J]. 浙江农业学报, 2024, 36(6): 1368-1378.

CHENG Chen, DONG Chaoyang, ZHENG Shenghong, ZHOU Yubo, ZHONG Ning, LI Wenming, ZHU Yangchun, DING Fenghua, FENG Liping, LI Zhenfa. Comparison of simulation accuracy of leaf age models for horticultural crops driven by light and temperature factors[J]. Acta Agriculturae Zhejiangensis, 2024, 36(6): 1368-1378.

图/表 6

表1 供试品种及试验设计

Table 1 Crop varieties in experiment

作物类型 Crop type	试验地点 Experiment position	品种 Variety	试验起始日期 Experiment start date	试验结束日期 Experiment end date	辐射数据 Radiation data
黄瓜Cucumber	武清区Wuqing District	津盛206 Jinsheng 206(JS)	2018-09-20	2019-02-28	√
			2018-10-17^*	2019-02-28	√
			2018-11-11	2019-02-28	√
			2019-03-10	2019-07-24	√
			2019-03-26^*	2019-07-24	√
			2019-04-10	2019-07-24	√
			2019-09-20	2020-03-28	√
			2019-10-10^*	2020-04-05	√
			2019-11-11	2020-04-19	√
郁金香Tulip	顺义区杨镇	粉色印象Fenseyinxiang(PI)	2016-12-19	2017-03-17	×
	Yang Town, Shunyi District		2016-12-29^*	2017-03-21	×
			2017-01-08	2017-03-28	×
		白日梦Bairimeng(D)	2016-12-19	2017-03-20	×
			2016-12-29^*	2017-03-24	×
			2017-01-08	2017-03-29	×
		艾斯米Aisimi(E)	2016-12-19	2017-03-25	×
			2016-12-29^*	2017-03-31	×
			2017-01-08	2017-04-06	×
		夜皇后Yehuanghou(QN)	2016-12-19	2017-04-01	×
			2016-12-29^*	2017-04-08	×
			2017-01-08	2017-04-15	×
芹菜Celery	武清区Wuqing Distrcit	尤文图斯Youwentusi(J)	2018-09-10	2019-03-14	√
			2018-10-10^*	2019-03-14	√
			2019-09-10	2020-04-14	√
			2019-09-24^*	2020-04-14	√
			2019-10-09	2020-04-14	√
	丽水学院Lishui University	尤文图斯Youwentusi(J)	2021-09-10	2022-05-13	×
			2021-10-08^*	2022-05-13	×
			2021-11-09	2022-05-13	×
菠菜Spinach	丽水学院Lishui University	大叶菠菜Dayebocai(DY)	2021-09-27	2022-03-19	×
			2021-11-23^*	2022-03-19	×
香芹Parsley	丽水学院Lishui University	四季香芹Sijixiangqin(SJ)	2021-09-27	2022-03-19	×
			2021-10-26^*	2022-03-19	×
茶Tea	松阳县Songyang County	中黄2号Zhonghuang 2(G1)、龙井Longjing(G2)、早奶白 Zaonaibai(W1)、安吉Anji (W2)、黄金甲Huangjinjia (Y1)、黄金玉Huangjinyu(Y2)	2021-12-08(斋坛乡 Zhaitan Village)^* 2021-12-08 (黄埠头村 Huangbutou Village)	——	×

表1 供试品种及试验设计

Table 1 Crop varieties in experiment

作物类型 Crop type	试验地点 Experiment position	品种 Variety	试验起始日期 Experiment start date	试验结束日期 Experiment end date	辐射数据 Radiation data
黄瓜Cucumber	武清区Wuqing District	津盛206 Jinsheng 206(JS)	2018-09-20	2019-02-28	√
			2018-10-17^*	2019-02-28	√
			2018-11-11	2019-02-28	√
			2019-03-10	2019-07-24	√
			2019-03-26^*	2019-07-24	√
			2019-04-10	2019-07-24	√
			2019-09-20	2020-03-28	√
			2019-10-10^*	2020-04-05	√
			2019-11-11	2020-04-19	√
郁金香Tulip	顺义区杨镇	粉色印象Fenseyinxiang(PI)	2016-12-19	2017-03-17	×
	Yang Town, Shunyi District		2016-12-29^*	2017-03-21	×
			2017-01-08	2017-03-28	×
		白日梦Bairimeng(D)	2016-12-19	2017-03-20	×
			2016-12-29^*	2017-03-24	×
			2017-01-08	2017-03-29	×
		艾斯米Aisimi(E)	2016-12-19	2017-03-25	×
			2016-12-29^*	2017-03-31	×
			2017-01-08	2017-04-06	×
		夜皇后Yehuanghou(QN)	2016-12-19	2017-04-01	×
			2016-12-29^*	2017-04-08	×
			2017-01-08	2017-04-15	×
芹菜Celery	武清区Wuqing Distrcit	尤文图斯Youwentusi(J)	2018-09-10	2019-03-14	√
			2018-10-10^*	2019-03-14	√
			2019-09-10	2020-04-14	√
			2019-09-24^*	2020-04-14	√
			2019-10-09	2020-04-14	√
	丽水学院Lishui University	尤文图斯Youwentusi(J)	2021-09-10	2022-05-13	×
			2021-10-08^*	2022-05-13	×
			2021-11-09	2022-05-13	×
菠菜Spinach	丽水学院Lishui University	大叶菠菜Dayebocai(DY)	2021-09-27	2022-03-19	×
			2021-11-23^*	2022-03-19	×
香芹Parsley	丽水学院Lishui University	四季香芹Sijixiangqin(SJ)	2021-09-27	2022-03-19	×
			2021-10-26^*	2022-03-19	×
茶Tea	松阳县Songyang County	中黄2号Zhonghuang 2(G1)、龙井Longjing(G2)、早奶白 Zaonaibai(W1)、安吉Anji (W2)、黄金甲Huangjinjia (Y1)、黄金玉Huangjinyu(Y2)	2021-12-08(斋坛乡 Zhaitan Village)^* 2021-12-08 (黄埠头村 Huangbutou Village)	——	×

表2 叶龄模拟模型逐步回归集成参数

Table 2 Integrated parameters of leaf age simulation model

方法 Methods	直接集成逻辑a_NDirect integration logic				方法 Methods	分步集成逻辑${{a}_{N\_}}_{\text{sub}}$Stepwise integration logic
	不含辐热积方法 Excluding M_TEP		含辐热积方法 Including M_TEP			不含辐热积方法 Excluding M_TEP		含辐热积方法 Including M_TEP
	逐日Daily	逐时Hourly	逐日Daily	逐时Hourly		逐日Daily	逐时Hourly	逐日Daily	逐时Hourly
M_MM	—	0.380 6	-0.422 0	—	M_TD	—	0.309 8	-0.077 9	-0.266 9
M_AAA	—	—	—	—	M_AT	0.494 6	0.186 9	—	0.563 4
M_EAA	—	—	—	—	M_PDT	0.517 9	0.505 8	0.963 1	0.483 4
M_{PDT_1}	0.278 5	0.515 8	1.260 4	—	M_TEP			0.093 2	0.207 1
M_{PDT_2}	0.411 3	0.197 6	-0.805 5	1.940 7	${{c}_{N\_}}_{\text{sub}}$	-0.252 0	0.315 5	2.544 4	2.066 3
M_{TEP_1}			0.486 6	-0.204 0	R²	0.971 7	0.988 6	0.934 2	0.943 3
M_{TEP_2}			-0.570 4	—
M_AAL	0.304 0	—	—	-0.651 3
M_EAL	—	0.114 5	10.071 9	—
M_{PDT_3}	0.918 4	—	—	—
M_{PDT_4}	-1.623 6	—	—	-2.034 5
M_{TEP_3}			—	0.197 1
M_{TEP_4}			—	—
M_ABA	-2.115 2	—	—	0.899 1
M_EBA	0.222 0	0.937 1	—	—
M_ACA	3.481 1	—	—	—
M_ECA	—	—	—	0.363 2
M_ABL	3.887 5	-0.440 1	5.975 2	1.568 9
M_EBL	-1.141 1	-0.281 9	-4.662 9	-1.096 6
M_ACL	-3.591 8	—	-4.930 6	—
M_ECL	—	-0.415 3	-5.533 8	—
M_DN	—		0.150 4
c_N	-0.593 3	0.926 0	-1.974 8	1.300 5
R²	0.981 8	0.995 3	0.967 4	0.967 4

图1 直接集成逻辑下叶龄模拟模型验证图 a,时间尺度;b,作物种类;c,集成方式。为了便于观察,叶龄模型模拟精度最高的处理标记为红色、模拟精度很高的处理标记为绿色、模拟精度较高的处理标记为蓝色、其余模拟精度水平的处理标记为黑色。下同。

Fig.1 Validation of leaf age simulation model under direct integration logic a, Time scale; b, Crop type; c, Integration methods.For ease of observation, treatments with the highest simulation accuracy of the leaf age model are labelled in red, with very high simulation accuracy are labelled in green, with high simulation accuracy are labelled in blue, and the rest of the simulation accuracy levels are labelled in black. The same as below.

表3 直接集成逻辑下叶龄模拟模型的验证统计量

Table 3 Validation statistics of leaf age simulation model under direct integration logic

对象类型Object type		$X - o b s$ ±SD/d	$X - s i m$ ±SD/d	N	α	β	R²	RMSE/d	NRMSE/%	MAE/d	MRE/%
时间尺度	逐日尺度Daily scale	86.87±67.62	87.70±67.21	900	0.99	-0.34	0.98	10.37	11.93	6.68	13.96
Time scale	逐时尺度Hourly scale	86.87±67.62	85.90±66.72	900	1.00	0.58	0.98	9.01	10.37	5.59	10.43
作物类型	菠菜Spinach	85.00±38.79	87.16±36.52	168	1.03	-4.88	0.94	9.54	11.23	6.66	7.84
Crop type	茶Tea	222.44±59.59	219.95±61.30	216	0.95	12.56	0.96	11.92	5.36	8.93	4.60
	黄瓜Cucumber	60.66±32.80	61.18±33.63	600	0.94	2.98	0.93	8.60	14.18	5.03	10.51
	芹菜Celery	78.74±36.86	79.64±37.15	456	0.95	2.87	0.92	10.48	13.31	7.18	10.77
	香芹Parsley	108.81±40.46	105.49±38.60	192	1.00	3.04	0.92	12.22	11.23	7.79	8.19
	郁金香Tulip	5.07±3.84	4.85±3.45	168	0.99	0.28	0.79	1.78	35.12	1.24	40.75
集成方法	${{M}_{I\_}}_{\text{dirave}}$	86.87±67.70	86.58±66.71	300	1.00	-0.02	0.98	10.01	11.52	7.47	10.99
Integration	${{M}_{I\_}}_{\text{dirmax}}$	86.87±67.70	87.06±65.37	300	1.01	-0.67	0.94	16.14	18.58	10.94	16.46
methods	${{M}_{I\_}}_{\text{dirmed}}$	86.87±67.70	86.37±67.77	300	0.99	1.55	0.98	10.13	11.66	7.59	11.79
	${{M}_{I\_}}_{\text{dirstep}}$	86.87±67.70	86.42±67.43	300	1.00	0.57	0.99	7.02	8.08	4.94	11.20
	${{M}_{I\_}}_{\text{dirbp}}$	86.87±67.70	87.47±67.33	300	1.00	-0.57	0.99	7.23	8.32	5.27	16.33
	${{M}_{I\_}}_{\text{direlman}}$	86.87±67.70	86.91±67.63	300	1.00	-0.11	1.00	1.00	1.16	0.60	6.38

表3 直接集成逻辑下叶龄模拟模型的验证统计量

Table 3 Validation statistics of leaf age simulation model under direct integration logic

对象类型Object type		$X - o b s$ ±SD/d	$X - s i m$ ±SD/d	N	α	β	R²	RMSE/d	NRMSE/%	MAE/d	MRE/%
时间尺度	逐日尺度Daily scale	86.87±67.62	87.70±67.21	900	0.99	-0.34	0.98	10.37	11.93	6.68	13.96
Time scale	逐时尺度Hourly scale	86.87±67.62	85.90±66.72	900	1.00	0.58	0.98	9.01	10.37	5.59	10.43
作物类型	菠菜Spinach	85.00±38.79	87.16±36.52	168	1.03	-4.88	0.94	9.54	11.23	6.66	7.84
Crop type	茶Tea	222.44±59.59	219.95±61.30	216	0.95	12.56	0.96	11.92	5.36	8.93	4.60
	黄瓜Cucumber	60.66±32.80	61.18±33.63	600	0.94	2.98	0.93	8.60	14.18	5.03	10.51
	芹菜Celery	78.74±36.86	79.64±37.15	456	0.95	2.87	0.92	10.48	13.31	7.18	10.77
	香芹Parsley	108.81±40.46	105.49±38.60	192	1.00	3.04	0.92	12.22	11.23	7.79	8.19
	郁金香Tulip	5.07±3.84	4.85±3.45	168	0.99	0.28	0.79	1.78	35.12	1.24	40.75
集成方法	${{M}_{I\_}}_{\text{dirave}}$	86.87±67.70	86.58±66.71	300	1.00	-0.02	0.98	10.01	11.52	7.47	10.99
Integration	${{M}_{I\_}}_{\text{dirmax}}$	86.87±67.70	87.06±65.37	300	1.01	-0.67	0.94	16.14	18.58	10.94	16.46
methods	${{M}_{I\_}}_{\text{dirmed}}$	86.87±67.70	86.37±67.77	300	0.99	1.55	0.98	10.13	11.66	7.59	11.79
	${{M}_{I\_}}_{\text{dirstep}}$	86.87±67.70	86.42±67.43	300	1.00	0.57	0.99	7.02	8.08	4.94	11.20
	${{M}_{I\_}}_{\text{dirbp}}$	86.87±67.70	87.47±67.33	300	1.00	-0.57	0.99	7.23	8.32	5.27	16.33
	${{M}_{I\_}}_{\text{direlman}}$	86.87±67.70	86.91±67.63	300	1.00	-0.11	1.00	1.00	1.16	0.60	6.38

图2 分步集成逻辑下叶龄模拟模型的验证图

Fig.2 Validation of leaf age simulation model under stepwise integration logic

表4 分步集成逻辑下叶龄模拟模型的验证统计量

Table 4 Validation statistics of leaf age simulation model under stepwise integration logic

对象类型Object type		$X - o b s$ ±SD/d	$X - s i m$ ±SD/d	N	α	β	R²	RMSE/d	NRMSE/%	MAE/d	MRE/%
时间尺度	逐日尺度Daily scale	86.87±67.62	87.38±66.83	900	1.00	-0.41	0.97	10.81	12.45	7.33	13.81
Time scale	逐时尺度Hourly scale	86.87±67.62	86.27±67.19	900	1.00	0.58	0.99	7.51	8.65	5.57	9.92
作物类型	菠菜Spinach	85.00±38.79	86.78±35.93	168	1.05	-6.46	0.95	8.77	10.31	6.67	7.16
Crop type	茶Tea	222.44±59.59	219.28±61.98	216	0.94	15.74	0.96	12.59	5.66	9.80	4.98
	黄瓜Cucumber	60.66±32.80	60.56±33.32	600	0.95	3.40	0.92	9.30	15.33	6.00	12.38
	芹菜Celery	78.74±36.86	80.51±38.17	456	0.93	3.61	0.93	9.96	12.65	7.39	10.73
	香芹Parsley	108.81±40.46	106.43±38.68	192	1.03	-0.71	0.97	7.73	7.10	6.51	6.95
	郁金香Tulip	5.07±3.84	5.12±3.25	168	1.12	-0.65	0.90	1.27	25.02	0.90	32.28
集成方法	${{M}_{I\_}}_{\text{subave}}$	86.87±67.70	86.89±67.00	300	1.00	0.19	0.97	10.75	12.37	7.47	11.16
Integration	${{M}_{I\_}}_{\text{submax}}$	86.87±67.70	87.12±66.79	300	1.00	-0.04	0.97	11.93	13.73	8.22	12.49
methods	${{M}_{I\_}}_{\text{submed}}$	86.87±67.70	86.69±67.54	300	0.99	0.99	0.98	10.25	11.80	7.31	11.19
	${{M}_{I\_}}_{\text{substep}}$	86.87±67.70	86.60±67.15	300	1.00	0.23	0.99	8.25	9.50	6.19	10.45
	${{M}_{I\_}}_{\text{subbp}}$	86.87±67.70	86.67±66.77	300	1.01	-0.35	0.99	8.19	9.43	6.25	12.18
	${{M}_{I\_}}_{\text{subel}man}$	86.87±67.70	87.00±67.25	300	1.00	-0.49	1.00	4.70	5.41	3.25	13.72

表4 分步集成逻辑下叶龄模拟模型的验证统计量

Table 4 Validation statistics of leaf age simulation model under stepwise integration logic

对象类型Object type		$X - o b s$ ±SD/d	$X - s i m$ ±SD/d	N	α	β	R²	RMSE/d	NRMSE/%	MAE/d	MRE/%
时间尺度	逐日尺度Daily scale	86.87±67.62	87.38±66.83	900	1.00	-0.41	0.97	10.81	12.45	7.33	13.81
Time scale	逐时尺度Hourly scale	86.87±67.62	86.27±67.19	900	1.00	0.58	0.99	7.51	8.65	5.57	9.92
作物类型	菠菜Spinach	85.00±38.79	86.78±35.93	168	1.05	-6.46	0.95	8.77	10.31	6.67	7.16
Crop type	茶Tea	222.44±59.59	219.28±61.98	216	0.94	15.74	0.96	12.59	5.66	9.80	4.98
	黄瓜Cucumber	60.66±32.80	60.56±33.32	600	0.95	3.40	0.92	9.30	15.33	6.00	12.38
	芹菜Celery	78.74±36.86	80.51±38.17	456	0.93	3.61	0.93	9.96	12.65	7.39	10.73
	香芹Parsley	108.81±40.46	106.43±38.68	192	1.03	-0.71	0.97	7.73	7.10	6.51	6.95
	郁金香Tulip	5.07±3.84	5.12±3.25	168	1.12	-0.65	0.90	1.27	25.02	0.90	32.28
集成方法	${{M}_{I\_}}_{\text{subave}}$	86.87±67.70	86.89±67.00	300	1.00	0.19	0.97	10.75	12.37	7.47	11.16
Integration	${{M}_{I\_}}_{\text{submax}}$	86.87±67.70	87.12±66.79	300	1.00	-0.04	0.97	11.93	13.73	8.22	12.49
methods	${{M}_{I\_}}_{\text{submed}}$	86.87±67.70	86.69±67.54	300	0.99	0.99	0.98	10.25	11.80	7.31	11.19
	${{M}_{I\_}}_{\text{substep}}$	86.87±67.70	86.60±67.15	300	1.00	0.23	0.99	8.25	9.50	6.19	10.45
	${{M}_{I\_}}_{\text{subbp}}$	86.87±67.70	86.67±66.77	300	1.01	-0.35	0.99	8.19	9.43	6.25	12.18
	${{M}_{I\_}}_{\text{subel}man}$	86.87±67.70	87.00±67.25	300	1.00	-0.49	1.00	4.70	5.41	3.25	13.72

参考文献 27

[1]	PANTIN F, SIMONNEAU T, MULLER B. Coming of leaf age: control of growth by hydraulics and metabolics during leaf ontogeny[J]. The New Phytologist, 2012, 196(2): 349-366.
[2]	陈凯利, 李建明, 贺会强, 等. 水分对番茄不同叶龄叶片光合作用的影响[J]. 生态学报, 2013, 33(16): 4919-4929.
	CHEN K L, LI J M, HE H Q, et al. Effects of water on photosynthesis in different age of tomato leaves[J]. Acta Ecologica Sinica, 2013, 33(16): 4919-4929. (in Chinese with English abstract)
[3]	程陈, 冯利平, 薛庆禹, 等. 日光温室黄瓜生长发育模拟模型[J]. 应用生态学报, 2019, 30(10): 3491-3500.
	CHENG C, FENG L P, XUE Q Y, et al. Simulation model for cucumber growth and development in sunlight greenhouse[J]. Chinese Journal of Applied Ecology, 2019, 30(10): 3491-3500. (in Chinese with English abstract)
[4]	魏广彬, 徐蕊, 孙和平, 等. 叶龄模型在水稻上应用的检验与比较[J]. 江苏农业学报, 2013, 29(4): 696-707.
	WEI G B, XU R, SUN H P, et al. Validation and comparison of the precision of leaf emergence models on rice[J]. Jiangsu Journal of Agricultural Sciences, 2013, 29(4): 696-707. (in Chinese with English abstract)
[5]	DINSSA F F, YANG R Y, LEDESMA D R, et al. Effect of leaf harvest on grain yield and nutrient content of diverse amaranth entries[J]. Scientia Horticulturae, 2018, 236: 146-157.
[6]	ELLIS R H, QI A, SUMMERFIELD R J, et al. Rates of leaf appearance and panicle development in rice (Oryza sativa L.): a comparison at three temperatures[J]. Agricultural and Forest Meteorology, 1993, 66(3/4): 129-138.
[7]	姜会飞, 郭勇, 张玉莹, 等. 不同下限基点温度对积温模型模拟效果的影响[J]. 中国农业大学学报, 2018, 23(5): 131-141.
	JIANG H F, GUO Y, ZHANG Y Y, et al. Impact of base temperature on the growing degree-day and simulation effect of GDD model[J]. Journal of China Agricultural University, 2018, 23(5): 131-141. (in Chinese with English abstract)
[8]	张智优, 曹宏鑫, 陈兵林, 等. 设施番茄发育期与叶龄动态模拟模型研究[J]. 中国农业气象, 2011, 32(4): 550-557.
	ZHANG Z Y, CAO H X, CHEN B L, et al. Research on the simulation models of phenophase and leaf number of controlled tomato[J]. Chinese Journal of Agrometeorology, 2011, 32(4): 550-557. (in Chinese with English abstract)
[9]	程陈, 董朝阳, 黎贞发, 等. 日光温室芹菜外观形态及干物质积累分配模拟模型[J]. 农业工程学报, 2021, 37(10): 142-151.
	CHENG C, DONG C Y, LI Z F, et al. Simulation model of external morphology and dry matter accumulation and distribution of celery in solar greenhouse[J]. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37(10): 142-151. (in Chinese with English abstract)
[10]	TREWAVAS A. A brief history of systems biology. “Every object that biology studies is a system of systems.” Francois Jacob (1974)[J]. The Plant Cell, 2006, 18(10): 2420-2430.
[11]	余卫东, 冯利平. 小时和日步长热时对夏玉米生育期模拟的影响[J]. 农业工程学报, 2021, 37(7): 131-139.
	YU W D, FENG L P. Comparison of the simulation effects of summer maize phenology derived from hourly and daily time step thermal units[J]. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37(7): 131-139. (in Chinese with English abstract)
[12]	徐立鸿, 孟凡峥, 蔚瑞华. 秒尺度温室番茄作物-环境互作模型构建与验证[J]. 农业工程学报, 2021, 37(8): 212-222.
	XU L H, MENG F Z, WEI R H. Development and verification of tomato crop-environment interaction model in second timescale greenhouse[J]. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37(8): 212-222. (in Chinese with English abstract)
[13]	MUSTAFA S M T, NOSSENT J, GHYSELS G, et al. Integrated Bayesian Multi-model approach to quantify input, parameter and conceptual model structure uncertainty in groundwater modeling[J]. Environmental Modelling & Software, 2020, 126: 104654.
[14]	ASSENG S, EWERT F, ROSENZWEIG C, et al. Uncertainty in simulating wheat yields under climate change[J]. Nature Climate Change, 2013, 3(9): 827-832.
[15]	MARTRE P, WALLACH D, ASSENG S, et al. Multimodel ensembles of wheat growth: many models are better than one[J]. Global Change Biology, 2015, 21(2): 911-925.
[16]	ROSENZWEIG C, JONES J W, HATFIELD J L, et al. The Agricultural Model Intercomparison and Improvement Project (AgMIP): protocols and pilot studies[J]. Agricultural and Forest Meteorology, 2013, 170: 166-182.
[17]	ZHAO C, LIU B, XIAO L J, et al. A SIMPLE crop model[J]. European Journal of Agronomy, 2019, 104: 97-106.
[18]	程陈, 李春, 李文明, 等. 园艺作物发育期和采收期模拟模型的最优模拟路径[J]. 农业工程学报, 2023, 39(12): 158-167.
	CHENG C, LI C, LI W M, et al. Optimal path of the simulation model in horticultural crop development and harvest period[J]. Transactions of the Chinese Society of Agricultural Engineering, 2023, 39(12): 158-167. (in Chinese with English abstract)
[19]	辛菊琴, 蒋艳, 舒少龙. 综合用户偏好模型和BP神经网络的个性化推荐[J]. 计算机工程与应用, 2013, 49(2): 57-60, 96.
	XIN J Q, JIANG Y, SHU S L. Personal recommendation algorithm with customer preference model and BP neural networks[J]. Computer Engineering and Applications, 2013, 49(2): 57-60, 96. (in Chinese with English abstract)
[20]	程陈, 冯利平, 董朝阳, 等. 利用Elman神经网络的华北棚型日光温室室内环境要素模拟[J]. 农业工程学报, 2021, 37(13): 200-208.
	CHENG C, FENG L P, DONG C Y, et al. Simulation of inside environmental factors in solar greenhouses using Elman neural network in North China[J]. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37(13): 200-208. (in Chinese with English abstract)
[21]	夏克文, 李昌彪, 沈钧毅. 前向神经网络隐含层节点数的一种优化算法[J]. 计算机科学, 2005, 32(10): 143-145.
	XIA K W, LI C B, SHEN J Y. An optimization algorithm on the number of hidden layer nodes in feed-forward neural network[J]. Computer Science, 2005, 32(10): 143-145. (in Chinese with English abstract)
[22]	程陈, 黎贞发, 董朝阳, 等. 日光温室黄瓜和芹菜不同位置消光系数模拟及验证[J]. 农业工程学报, 2020, 36(21): 243-252.
	CHENG C, LI Z F, DONG C Y, et al. Simulation and validation of extinction coefficient at different positions of cucumber and celery in solar greenhouse[J]. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(21): 243-252. (in Chinese with English abstract)
[23]	CHENG C, FENG L P, BIENVENIDO BARCENA J F, et al. A growth model based on standardized growing degree days for hydroponic fresh cut tulip in solar greenhouses[J]. European Journal of Horticultural Science, 2022, 87(4): 1-13.
[24]	PURCELL L C. Comparison of thermal units derived from daily and hourly temperatures[J]. Crop Science, 2003, 43(5): 1874-1879.
[25]	丁为民, 汪小旵, 李毅念, 等. 温室环境控制与温室模拟模型研究现状分析[J]. 农业机械学报, 2009, 40(5): 162-168.
	DING W M, WANG X C, LI Y N, et al. Review on environmental control and simulation models for greenhouses[J]. Transactions of the Chinese Society for Agricultural Machinery, 2009, 40(5): 162-168. (in Chinese with English abstract)
[26]	HADASCH S, FORKMAN J, PIEPHO H P. Cross-validation in AMMI and GGE models: a comparison of methods[J]. Crop Science, 2017, 57(1): 264-274.
[27]	ZHENG J H, ZHANG S. Improving rice phenology simulations based on the Bayesian model averaging method[J]. European Journal of Agronomy, 2023, 142: 126646.

光温因子驱动的园艺作物叶龄模型模拟精度比较

Comparison of simulation accuracy of leaf age models for horticultural crops driven by light and temperature factors

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 27

相关文章 15

编辑推荐

Metrics

本文评价

[1]	朱冬琴, 冯全, 张建华. 基于剪枝的植物病害识别方法[J]. 浙江农业学报, 2023, 35(6): 1462-1472.
[2]	樊闯, 赵子皓, 张雪松, 杨沈斌. 基于BP神经网络的一季稻发育期预测模型[J]. 浙江农业学报, 2023, 35(2): 434-444.
[3]	柴琴琴, 曾建, 张勋. 基于贝叶斯优化卷积神经网络的金线莲伪品鉴别[J]. 浙江农业学报, 2022, 34(2): 391-396.
[4]	李超, 李锋, 黄炜嘉. 基于并联卷积神经网络的水果品种识别[J]. 浙江农业学报, 2022, 34(11): 2533-2541.
[5]	吉训生, 姜晓卫, 夏圣奎. 基于LSTM-Kalman模型的蛋鸡产蛋率预测方法[J]. 浙江农业学报, 2021, 33(9): 1730-1739.
[6]	张晴晴, 刘连忠, 宁井铭, 吴国栋, 江朝晖, 李孟杰, 李栋梁. 基于YOLOV3优化模型的复杂场景下茶树嫩芽识别[J]. 浙江农业学报, 2021, 33(9): 1740-1747.
[7]	冼炜轩, 尚国琲, 刘巧芹, 刘玉. 基于神经网络法与加权模型的乡村旅游用地竞争力评价研究——以北京市密云区为例[J]. 浙江农业学报, 2021, 33(8): 1519-1528.
[8]	杨红云, 罗建军, 孙爱珍, 万颖, 易文龙. 基于图像特征的水稻叶片全氮含量估测模型研究[J]. 浙江农业学报, 2020, 32(12): 2232-2243.
[9]	鲍烈, 王曼韬, 刘江川, 文波, 明月. 基于卷积神经网络的小麦产量预估方法[J]. 浙江农业学报, 2020, 32(12): 2244-2252.
[10]	王枭轩, 孟庆岩, 张海香, 魏香琴, 杨泽楠. 基于粒子群神经网络模型反演玉米、小麦叶面积指数[J]. 浙江农业学报, 2019, 31(7): 1170-1176.
[11]	蒋丰千, 李旸, 余大为, 孙敏, 张恩宝. 基于Caffe卷积神经网络的大豆病害检测系统[J]. 浙江农业学报, 2019, 31(7): 1177-1183.
[12]	李颀, 赵洁, 杨柳, 王俊, 高一星. 基于GA-BP神经网络和特征向量优化组合的黄瓜叶片病斑识别[J]. 浙江农业学报, 2019, 31(3): 487-495.
[13]	金秀, 卢杰, 傅运之, 王帅, 许高健, 李绍稳. 基于深度卷积神经网络的小麦赤霉病高光谱病症点分类方法[J]. 浙江农业学报, 2019, 31(2): 315-325.
[14]	胡志辉, 汪艳杰, 张丽琴. 菜用大豆施肥后荧光、光谱、光合等参数对产量的预测[J]. 浙江农业学报, 2018, 30(8): 1355-1362.
[15]	杨国亮, 许楠, 康乐乐, 龚曼, 洪志阳. 基于参数指数非线性残差神经网络的脐橙病变叶片识别[J]. 浙江农业学报, 2018, 30(6): 1073-1081.