A Time Series Data Filling Method Based on LSTM-Taking the Stem Moisture as an Example.

Yue Zhao,Wei Song,Yandong Zhao,Chao Gao

doi:10.3390/s20185045

Abstract

In order to solve the problem of data loss in sensor data collection, this paper took the stem moisture data of plants as the object, and compared the filling value of missing data in the same data segment with different data filling methods to verify the validity and accuracy of the stem water filling data of the LSTM (Long Short-Term Memory) model. This paper compared the accuracy of missing stem water data for plants under different data filling methods to solve the problem of data loss in sensor data collection. Original stem moisture data was selected from Lagerstroemia Indica which was planted in the Haidian District of Beijing in June 2017. Part of the data which treated as missing data was manually deleted. Interpolation methods, time series statistical methods, the RNN (Recurrent Neural Network), and LSTM neural network were used to fill in the missing part and the filling results were compared with the original data. The result shows that the LSTM has more accurate performance than the RNN. The error values of the bidirectional LSTM model are the smallest among several models. The error values of the bidirectional LSTM are much lower than other methods. The MAPE (mean absolute percent error) of the bidirectional LSTM model is 1.813%. After increasing the length of the training data, the results further proved the effectiveness of the model. Further, in order to solve the problem of one-dimensional filling error accumulation, the LSTM model is used to conduct the multi-dimensional filling experiment with environmental data. After comparing the filling results of different environmental parameters, three environmental parameters of air humidity, photosynthetic active radiation, and soil temperature were selected as input. The results show that the multi-dimensional filling can greatly extend the sequence length while maintaining the accuracy, and make up for the defect that the one-dimensional filling accumulates errors with the increase of the sequence. The minimum MAPE of multidimensional filling is 1.499%. In conclusion, the data filling method based on LSTM neural network has a great advantage in filling the long-lost time series data which would provide a new idea for data filling.

Highlights

Water is the basis of plant metabolism and is an important component of plant cells [1]
High-precision data filling can deal with data missing due to various reasons
In order to better cope with the long-term data loss caused failure of sensors, this paper proposes a method of filling missing data based on LSTM

Summary

Introduction

Water is the basis of plant metabolism and is an important component of plant cells [1]. The filling method using a neural network [14] can be applied to any nonlinear relation function and has a self-learning ability Still, it requires large-scale data samples, and overfitting and generalization problems have always existed. We can get the global optimal solution by using the support vector machine [15] to fill the data This method requires less data scale compared to traditional neural networks. The LSTM neural network model, optimized on the basis of RNN [23], has achieved good results in areas such as semantic analysis and image recognition that require strong historical information memory [24,25,26], but it is rarely used in the field of physiological data analysis. Using LSTM to fill data in two different environments, one-dimensional and multi-dimensional, has achieved better results than the traditional data filling method

Introduction to to LSTM

Unfold of of RNN

LSTM Model Construction

Calculation of Parameters in the First LSTM Layer

Dropout Layer

The Data Source

Model Training Result Analysis

The filling result of the

11. Filling results forfor different

Model Results and Analysis after Increasing the Training Data

Section 3.1.1.

Multidimensional LSTM Model Results Analysis