Agricultural drought rapid diagnosis and evaluation method coupling crop model and machine learning language

Abstract

The invention discloses an agricultural drought diagnosis and evaluation method coupling a crop model and a machine language. The method comprises the steps of S1, obtaining related data in a researcharea; S2, localizing a crop model in the research area by utilizing the data obtained in the step S1; S3, setting different drought and rainfall scene data according to different growth stages of crops, and inputting the data into the localized crop model to obtain simulation data of each grid point in the research area under each drought scene; S4, calculating a characteristic variable based onthe drought situation data and the corresponding crop model simulation data in S3; S5, taking the yield loss rate data simulated by the corresponding crop model as a prediction variable based on the characteristic variable in the step S4, constructing a sample data set, and inputting the sample data set into a random forest model to construct a crop drought vulnerability model; S6, using the cropdrought vulnerability model for diagnosing and evaluating the crop drought condition in the research time period.

Description

technical field [0001] The invention relates to the field of agricultural information technology, in particular to a method for quickly diagnosing and evaluating agricultural drought coupled with crop models and machine learning languages. Background technique [0002] As a complex and frequent extreme meteorological disaster, drought causes more than 43% of the global direct economic loss of all natural disasters every year, and the loss caused by my country accounts for about 42% of the global drought loss. Among them, agriculture has become one of the fields most affected by drought because of its closely related characteristics with weather. Agricultural drought refers to the phenomenon that the soil moisture is insufficient during the growth of crops, and the normal growth of crops is hindered due to the imbalance between water supply and demand. At present, there are mainly three types of research on agricultural drought and its impact on crop growth and yield: [00...

AI Technical Summary

Problems solved by technology

Although the crop model has a strong mechanism, most of the existing drought research based on the crop model has greatly simplified the real scene, which is difficult to reflect the real drought situation, and there are a lot of uncertainties in the simulation process of the model. Model simulation accuracy needs to be improved

For example, microwave remote sensing has all-day and all-weather observation capabilities because it is not disturbed by clouds, and can obtain a wide range of soil moisture. However, at present, it can only retrieve the soil moisture of the surface 2-5cm and the available public data is in China. The data is rough and the quality is not high

It can be seen that most of the existing soil moisture data have low temporal and spatial accuracy and mostly stay in shallow soil, while the root system of food crops is usually around 20cm (or even deeper), and most studies are difficult to reflect the real water stress status of crops

Images