茶小绿叶蝉高峰时间预测模型训练数据

茶小绿叶蝉病虫害的发生与气候变化密切相关，季节交替中差异最大的就是温度，温度条件是影响病虫害流行的重要因素。通过采集往年茶园大气温度数据，处理得到旬（每月分为上、中、下旬）平均温度、总旬温度。利用往年历史数据，拟合得到回归模型，预测茶小绿叶蝉高峰时间，依据预测虫害爆发时间与当前时间间隔，给出相应的虫害处理策略建议。第一，通过传感器以及物联网设备，采集茶园往年前三个月，1、2、3月每天的气温数据。 第二，根据采集到的每日气温数据，求和平均得到每旬的旬平均气温（每月有上中下旬，每旬十天，1~10号为上旬，11~20为中旬，21~月末为下旬），每年的旬平均气温求和得到旬平均总和气温。 第三，根据旬平均气温、旬平均总和气温以及当年茶小绿叶蝉虫口高峰开始时间数据，拟合得到回归模型，模型可以根据当年的前三月气温数据，预测茶小绿叶蝉爆发时间。

The occurrence of tea small green leafhopper pests and diseases is closely linked to climate change. Among all variables during seasonal transitions, temperature shows the most significant variability, and temperature conditions are a key factor driving the prevalence of these pests and diseases.

By collecting historical atmospheric temperature data from prior-year tea plantations, we processed the dataset to generate decadal average temperatures and total decadal cumulative temperatures. A "decad" refers to a 10-day period: each month is split into three decads—early (1st–10th), middle (11th–20th), and late (21st to the end of the month).

Using these historical records, a regression model was calibrated to predict the peak occurrence timing of tea small green leafhoppers. Targeted pest control strategy recommendations are provided based on the time gap between the predicted pest outbreak time and the current time.

The detailed data processing and modeling workflow is outlined below:
1. Collect daily temperature data for the first three months (January, February, March) of previous years from the target tea plantations using sensors and Internet of Things (IoT) devices.
2. Compute the decadal average temperature for each 10-day segment by summing and averaging the collected daily temperature data. Sum the decadal average temperatures for the entire year to derive the total annual cumulative decadal average temperature.
3. Fit a regression model using the decadal average temperatures, total annual cumulative decadal average temperature, and the recorded start time of the tea small green leafhopper population peak for the target year. The trained model can predict the outbreak time of tea small green leafhoppers based on the temperature data collected in the first three months of the target year.

搜集汇总

数据集介绍

特点

该数据集用于预测茶小绿叶蝉的高峰时间，包含269条记录，每日更新，主要字段包括气温相关数据和虫口高峰开始时间。通过历史气温数据拟合回归模型，预测虫害爆发时间并提供处理策略建议。