Soil heavy metal accumulation space-time prediction algorithm based on CA-LSTM-RF under deep learning framework

Through the CA-LSTM-RF algorithm under the deep learning framework, combined with cellular automata, long short-term memory networks and random forests, the problems of insufficient mining of spatial heterogeneity and time series characteristics in the spatiotemporal prediction of soil heavy metal accumulation in existing models are solved, and a more accurate prediction of soil heavy metal accumulation trends is achieved.

CN120688366AInactive Publication Date: 2025-09-23INST OF GEOGRAPHICAL SCI & NATURAL RESOURCE RES CAS
11 Cites 1 Cited by

Patent Information

Application Number
CN202510874917.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-06-27
Publication Date
2025-09-23
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Existing soil heavy metal accumulation models fail to effectively explore the variable characteristics in time series and geographic space when considering spatial heterogeneity, making it difficult to achieve refined simulation and accurate prediction of future spatiotemporal distribution.

Method used

The CA-LSTM-RF algorithm under the deep learning framework is combined with cellular automata, long short-term memory networks (LSTM) and random forests (RF). By simulating the surface runoff diffusion of heavy metals and environmental variable data, a spatiotemporal prediction model for soil heavy metal accumulation is constructed. The model is constructed using Keras of TensorFlow and the performance is evaluated.

Benefits of technology

Capturing the spatial details of soil heavy metal migration and distribution at the microscale improves the accuracy of depicting the accumulation trend of soil heavy metal pollution and achieves more accurate spatiotemporal predictions.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a CA-LSTM-RF soil heavy metal accumulation space-time prediction algorithm under a deep learning framework, and belongs to the technical field of soil heavy metal accumulation space-time prediction algorithms, and the algorithm comprises the steps: obtaining soil heavy metal content data of each sampling point in a plurality of historical periods in a target region and an environment variable data set affecting soil heavy metal accumulation; the method comprises the following steps: performing abnormal value detection, missing data supplementation, alignment processing, quantification processing, normalization processing and time sequence coding on data, performing cellular water flow direction judgment by improving a CA model and designing diffusion process simulation of adaptive time, and calculating heavy metal surface runoff diffusion by using a Manning formula. And taking the diffusion value of the heavy metal along with the surface runoff and the environment variable data as input, extracting a historical data relationship through LSTM, outputting a soil heavy metal accumulation prediction value at the current moment, and taking the output of the LSTM as input to construct an RF model to predict the spatial characteristics of the soil heavy metal.
Need to check novelty before this filing date? Find Prior Art