高寒冷凉地区日光温室温度变化规律分析与预报

Analysis and Forecast of Greenhouse Temperature Variation Regularity at Cold Area of High Latitude

为开展精细化设施农业气象预报服务,实现高产、稳产的反季节蔬菜栽培,达到农业防灾减灾和可持续发展的目的,利用青海省大通县国家现代农业示范园区日光温室小气候观测数据及气象站观测资料,分析了该地日光温室内温度变化规律,同时建立了该地日光温室内平均温度及最低温度预报模型。结果表明,室内年平均气温日变化均表现为"1升2降"的过程,08:00—14:00为升温阶段,最大升温速率多云天(5.46℃)>晴天(5.34℃)>阴天(1.6℃);14:00—21:00为快速降温阶段,降温速率多云天(2.79℃)>晴天(2.69℃)>阴天(1.56℃),21:00—08:00(次日)为缓慢降温阶段,降温速率晴天(0.57℃)>多云天(0.53℃)>阴天(0.49℃)。平均温度预报模型为Tave=3.991+0.688T1+0.113T4,预测值与实测值的相关系数(R2)达到0.7062,ABSe和RMSe为1.45、1.85℃,≤2%的准确率75%,≤4%的准确率96%;最低温度预报模型Tmin=-3.05+0.366T3+0.692T1-0.098T2,预测值与实测值相关系数(R2)达到0.8373,ABSe和RMSe为1.15、1.55℃,≤2%的准确率81%,≤4%的准确率99%,模型的模拟效果较好,具有较强的实用性。

For the sake of carrying out agrometeorological forecast service for the refined facilities, realizingoff-season vegetable cultivation with high and stable yield and thus achieving the aim of disaster preventionand reduction and sustainable development, in this paper the observation data of microclimate andmeteorological observation materials for the sunlight greenhouse in the national modern agriculturaldemonstrative zones, Datong County, Qinghai Province were applied to analyze the temperature variation lawsin this region and build the corresponding forecast model. The results showed that the all daily variations ofindoor annual average temperature appeared as a＂1 rise, 2 falls＂process. From 08：00 to 14：00, it was atemperature-rising phase, the maximal temperature-rising velocity was in an order as cloudy day（5.46℃） sunny day（5.34℃） rainy day（1.6℃）; from 14：00 to 21：00, it was a rapid temperature-falling phase, thetemperature-falling velocity was in an order as cloudy day（2.79℃） sunny day（2.69℃） rainy day（1.56℃）;and from 21：00 to 08：00（the next day）, it was an slow temperature- falling phase, the temperature- falling velocity was in an order as sunny day（0.57℃） cloudy day（0.53℃） rainy day（0.49℃）. A step- wiseregression method was applied and the average temperature forecast model and the lowest temperature forecastmodel were built for the sunlight greenhouse in the plateau area. The average temperature forecast model was Tave=3.991＋0.688T1＋0.113T4, the correlation coefficient（R2） of predicted value and actually measured valuereached 0.7062, the ABSe and RMSe were 1.45 and 1.85℃, the accuracy rate ≤2% was 75%, and the accuracyrate ≤4% was 96%. The lowest temperature forecast model was Tmin=-3.05＋0.366T3＋0.692T1-0.098T2, thecorrelation coefficient（R2） of predicted value and actually measured value reached 0.8373, the ABSe andRMSe were 1.15 and 1.55℃, the accuracy rate ≤2% was 81%, and the accuracy rate ≤4% was 99%. Themodels simulated soundly and showed better practicability.