{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T14:35:56Z","timestamp":1778250956912,"version":"3.51.4"},"reference-count":31,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2020,9,5]],"date-time":"2020-09-05T00:00:00Z","timestamp":1599264000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.3390\/s20185045","type":"journal-article","created":{"date-parts":[[2020,9,6]],"date-time":"2020-09-06T23:12:49Z","timestamp":1599433969000},"page":"5045","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":43,"title":["A Time Series Data Filling Method Based on LSTM\u2014Taking the Stem Moisture as an Example"],"prefix":"10.3390","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5117-5757","authenticated-orcid":false,"given":"Wei","family":"Song","sequence":"first","affiliation":[{"name":"School of Technology, Beijing Forestry University, Beijing 100083, China"},{"name":"Beijing Laboratory of Urban and Rural Ecological Environment, Beijing Forestry University, Beijing 100083, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0873-2826","authenticated-orcid":false,"given":"Chao","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Computer and Information Engineering, Beijing Technology and Business University, Beijing 100048, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Technology, Beijing Forestry University, Beijing 100083, China"},{"name":"Beijing Laboratory of Urban and Rural Ecological Environment, Beijing Forestry University, Beijing 100083, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yandong","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Technology, Beijing Forestry University, Beijing 100083, China"},{"name":"Beijing Laboratory of Urban and Rural Ecological Environment, Beijing Forestry University, Beijing 100083, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2020,9,5]]},"reference":[{"key":"ref_1","first-page":"60","article-title":"Preliminary study on precision irrigation system based on wireless sensor networks of acoustic emission technique for crop water stress","volume":"24","author":"Gao","year":"2008","journal-title":"Trans. Chin. Soc. Agric. Eng."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"126857","DOI":"10.1016\/j.snb.2019.126857","article-title":"Towards water-saving irrigation methodology: Field test of soil moisture profiling using flat thin mm-sized soil moisture sensors (MSMSs)","volume":"298","author":"Zhou","year":"2019","journal-title":"Sens. Actuators B Chem."},{"key":"ref_3","first-page":"3429","article-title":"Application research on big data promote agricultural modernization","volume":"48","author":"Xu","year":"2015","journal-title":"Sci. Agric. Sinica"},{"key":"ref_4","first-page":"310","article-title":"Quick reflection of moisture condition for plant using leaf tensity","volume":"46","author":"Wu","year":"2015","journal-title":"Trans. Chin. Soc. Agric. Mach."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"134227","DOI":"10.1016\/j.scitotenv.2019.134227","article-title":"Establishing a time series trend structure model to mine potential hydrological information from hydrometeorological time series data","volume":"698","author":"Yao","year":"2019","journal-title":"Sci. Total. Environ."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"111358","DOI":"10.1016\/j.rse.2019.111358","article-title":"Short and mid-term sea surface temperature prediction using time-series satellite data and LSTM-AdaBoost combination approach","volume":"233","author":"Xiao","year":"2019","journal-title":"Remote. Sens. Environ."},{"key":"ref_7","first-page":"1525","article-title":"Piecewise cloud approximation for time series mining. Knowledge-based systems","volume":"26","author":"Li","year":"2011","journal-title":"Control Decis."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1016\/j.agrformet.2017.01.009","article-title":"Evaluation of eddy covariance latent heat fluxes with independent lysimeter and sapflow estimates in a Mediterranean savannah ecosystem","volume":"236","author":"Migliavacca","year":"2017","journal-title":"Agric. For. Meteorol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1016\/j.agrformet.2007.08.011","article-title":"Comprehensive comparison of gap-filling techniques for eddy covariance net carbon fluxes","volume":"147","author":"Moffat","year":"2007","journal-title":"Agric. For. Meteorol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1726","DOI":"10.3724\/SP.J.1016.2012.01726","article-title":"Missing data imputation approach based on incomplete data clustering","volume":"35","author":"Wu","year":"2012","journal-title":"Chin. J. Comput."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1016\/j.atmosenv.2019.01.027","article-title":"Extreme gradient boosting model to estimate PM2.5 concentrations with missing-filled satellite data in China","volume":"202","author":"Chen","year":"2019","journal-title":"Atmospheric Environ."},{"key":"ref_12","first-page":"82","article-title":"Research on the method of filling missing data in data processing","volume":"28","author":"Hu","year":"2013","journal-title":"J. Hubei Univ. Technol."},{"key":"ref_13","first-page":"17","article-title":"Study on the long term prediction of annual electricity consumption using partial least square regressive model","volume":"23","author":"Wang","year":"2003","journal-title":"Proc. CSEE"},{"key":"ref_14","first-page":"261","article-title":"An empirical analysis of a neural network model for the time series forecasting of different industrial segments","volume":"8","author":"Zoucas","year":"2015","journal-title":"Int. J. Appl. Decis. Sci."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.ins.2014.12.031","article-title":"A weighted LS-SVM based learning system for time series forecasting","volume":"299","author":"Chen","year":"2015","journal-title":"Inf. Sci."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"100403","DOI":"10.1016\/j.ascom.2020.100403","article-title":"Predictive ARIMA Model for coronal index solar cyclic data","volume":"32","author":"Akhter","year":"2020","journal-title":"Astron. Comput."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/j.neucom.2019.05.099","article-title":"Improving forecasting accuracy of time series data using a new ARIMA-ANN hybrid method and empirical mode decomposition","volume":"361","author":"Buyuksahin","year":"2019","journal-title":"Neurocomputing"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/j.procs.2018.10.526","article-title":"Roll motion prediction using a hybrid deep learning and ARIMA model","volume":"144","author":"Suhermi","year":"2018","journal-title":"Procedia Comput. Sci."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"452","DOI":"10.1016\/j.eswa.2017.09.025","article-title":"Lane-changes prediction based on adaptive fuzzy neural network","volume":"91","author":"Tang","year":"2018","journal-title":"Exp. Sys. Appl."},{"key":"ref_20","first-page":"65","article-title":"A hybrid model based on time series models and neural network for forecasting wind speed in the Brazilian northeast region","volume":"28","author":"Lucio","year":"2018","journal-title":"Sustain. Energy Technol. Assess."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1016\/j.neucom.2019.07.034","article-title":"Multi-head CNN\u2013RNN for multi-time series anomaly detection: An industrial case study","volume":"363","author":"Canizo","year":"2019","journal-title":"Neurocomputing"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1016\/j.patcog.2019.03.030","article-title":"RNN based online handwritten word recognition in Devanagari and Bengali scripts using horizontal zoning","volume":"92","author":"Ghosh","year":"2019","journal-title":"Pattern Recognit."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Sak, H., Senior, A., and Beaufays, F. (2014, January 14\u201318). Long short-term memory recurrent neural network architectures for large scale acoustic modeling. Proceedings of the INTERSPEECH-2014, Singapore.","DOI":"10.21437\/Interspeech.2014-80"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"105765","DOI":"10.1016\/j.asoc.2019.105765","article-title":"Computer-aided diagnosis system combining FCN and Bi-LSTM model for efficient breast cancer detection from histopathological images","volume":"85","author":"Budak","year":"2019","journal-title":"Appl. Soft Comput."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1016\/j.apacoust.2019.07.033","article-title":"An effective gender recognition approach using voice data via deeper LSTM networks","volume":"156","author":"Ertam","year":"2019","journal-title":"Appl. Acoust."},{"key":"ref_26","first-page":"889","article-title":"Research advances and prospect of recognizing textual entailment and knowledge acquisition","volume":"40","author":"Guo","year":"2017","journal-title":"Chin. J. Comput."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"9628957","DOI":"10.1155\/2020\/9628957","article-title":"Evaluation of short-term freeway speed prediction based on periodic analysis using statistical models and machine learning models","volume":"2020","author":"Yang","year":"2020","journal-title":"J. Adv. Transp."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","article-title":"Frame wise phoneme classification with bidirectional LSTM and other neural network architectures","volume":"18","author":"Graves","year":"2005","journal-title":"Neural Netw."},{"key":"ref_30","unstructured":"Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012). ImageNet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"117197","DOI":"10.1016\/j.energy.2020.117197","article-title":"LSTM based long-term energy consumption prediction with periodicity","volume":"197","author":"Wang","year":"2020","journal-title":"Energy"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/18\/5045\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:07:06Z","timestamp":1760177226000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/18\/5045"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,5]]},"references-count":31,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2020,9]]}},"alternative-id":["s20185045"],"URL":"https:\/\/doi.org\/10.3390\/s20185045","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9,5]]}}}