甘肃小陇山林区甘肃鼢鼠危害面积的气象预测预报技术研究

A Study on Technique of Meterological Model for Forecasting Zekor Harmful Area at Xiaolongshan Forest in Gansu

甘肃小陇山林区位于我国四大自然植被区系(华北、华中、喜马拉雅、蒙新)交汇处的温带向亚热带过渡带,林业植物种类繁多、茂密,但区内地形、地貌复杂,气候差异大,林业生物灾害频繁,环境气候条件是其发生发展的主要制约因素。为此,进行区内林业生物灾害的气象预测预报技术研究,对林业有害生物灾害的预防、防治和林业产业发展具有显著的指导意义。利用逐步回归统计方法统计分析了影响甘肃小陇山林区甘肃鼢鼠危害面积的主要气象因子,建立了林区春、秋两季甘肃鼢鼠危害面积分区集成与全区综合统计预测预报数学模型。甘肃鼢鼠适宜温暖、较为干燥的气候环境,怕光、怕雨、怕高温高湿天气,林区暖冬天气气候和春、秋季温暖少雨天气、初夏较好的日照和适宜的温度条件配置是造成甘肃小陇山林区甘肃鼢鼠发展蔓延的主要气候原因。通过预测效果历史回代拟合检验,春、秋季16 a平均预测准确率均在97%以上。通过对2008年、2009年和2010年甘肃鼢鼠春、秋季危害面积进行试报检验,3 a平均试报误差分别为1.8、2.0和1.9、1.6,平均试报准确率均达98%以上,预测和试报效果均较理想,2种预报方法均可满足当前业务服务需求。

Xiaolongshan Forest is located in the transition region of temperate zone to subtropical zone which is also the junction area of four natural vegetation areas in China.There are lots of kinds of floristics and big differences in landform and climate in the forest.Forestry biological disasters happen frequently and the environmental climatic conditions are main limiting factors for biological disasters.The technique of forecasting biological disasters to protect the forest has been studied,which is of significance for forest development.The method of stepwise regression was used and the model for forecasting the zekor damage area in spring and autumn and statistical model were established.Zekor likes to live under warm and dry condition and dislikes light,rain,high temperature and high moisture.Zekor reproduces well in warm winter,in warm spring and autumn with little rain,and in sunshine and suitable temperature in early summer.The result of the model for forecasting showed that average prediction accuracy in spring and autumn was above 97% in the past 16 years.We tried to forecast the zekor harmful area in 2008,2009 and 2010 with the model.The result showed that the average error rate was 1.8,2.0 and 1.9,1.6 in 2008,2009 and 2010 respectively and the prediction accuracy was above 98%.The effect of forecast reached ideal level.We supposed that the models would meet the need of professional and service work.