Wheat yield estimation method and system suitable for extreme climate condition

Abstract

The invention discloses a wheat yield estimation method and system suitable for an extreme climate condition, and relates to the technical field of agriculture, and the method comprises the steps: obtaining a plurality of different training samples, wherein each training sample comprises a trend yield, an SPEI drought index, a dry and hot air effective day number, N average rainfall average values, N average temperature average values and M NDVI vegetation indexes corresponding to the total cultivated land of each county in the wheat area in a wheat growth period; training and optimizing the random forest model by taking a plurality of different training samples as input and taking the actual yield of the total cultivated land of each county corresponding to each training sample in each wheat growth period as output to obtain an optimized random forest model; and predicting the actual yield of the total cultivated land of the county to be subjected to yield estimation in the set wheat area in the growth period of the wheat to be predicted by using the optimized random forest model. The method can accurately estimate the yield of wheat under the extreme climate condition.

Description

technical field [0001] The invention relates to the field of agricultural technology, in particular to a method and system for estimating wheat yield under extreme weather conditions. Background technique [0002] From the first half of the 20th century to the present, CO in the Earth's atmosphere 2 The concentration increased significantly, the global average surface temperature rose by 0.74°C, and the warming trend became more and more serious. Abnormal global climate change has led to frequent occurrence of abnormal climate events, which have had a huge impact on agricultural production. Relevant studies have shown that agricultural production is affected by climate change to some extent, but overall the disadvantages outweigh the advantages. [0003] Agriculture is seriously affected by climate change. From 1986 to 2007, it experienced 21 consecutive warm winters. Among all kinds of agricultural meteorological disasters, drought and flood are the most important factor...

AI Technical Summary

Problems solved by technology

Breiman proposed the random forest algorithm in 2001. It is an integrated learning algorithm, which has the advantages of good stability, high prediction accuracy, and is not easy to produce over-fitting. It does not need to worry about the problem of multicollinearity. Compared with neural network and linear regression methods, its performance is more stable and it has strong anti-interference ability. Therefore, this algorithm has been widely used in flood risk analysis, remote sensing image processing, fire risk analysis, etc., but the current application There are very few studies on the random forest algorithm for crop yield estimation modeling under abnormal climate (extreme climate) conditions, and most of the current research has not verified the yield estimation model established in disaster years.

Even if there are studies that use the random forest algorithm to estimate the yield, they only use the original temperature and precipitation data to estimate the wheat yield, and cannot accurately estimate the wheat yield under extreme climate conditions (that is, in disaster years)

Images