{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T18:27:14Z","timestamp":1786127234751,"version":"3.56.0"},"reference-count":63,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"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>High-frequency monitoring of agrometeorological parameters is quintessential in the domain of Precision Agriculture (PA), where timeliness of collected observations and the ability to generate ahead-of-time predictions can substantially impact the crop yield. In this context, state-of-the-art internet-of-things (IoT)-based sensing platforms are often employed to generate, pre-process and assimilate real-time data from heterogeneous sensors and streaming data sources. Simultaneously, Time-Series Forecasting Algorithms (TSFAs) are responsible for generating reliable forecasts with a pre-defined forecast horizon and confidence. These TSFAs often rely on modelling the correlation between endogenous variables, the impact of exogenous variables on latent form and structural properties of data such as autocorrelation, periodicity, trend, pattern, and causality to approximate the model parameters. Traditionally, TSFAs such as the Holt\u2013Winters (HW) and Autoregressive family of models (ARIMA) apply a linear and parametric approach towards model approximation, whilst models like Support Vector Regression (SVRs) and Neural Networks (NNs) adhere to a non-linear, non-parametric approach for modelling the historical data. Recently, Deep-Learning-based TSFAs such as Recurrent Neural Networks (RNNs), and Long-Short-Term-Memory (LSTMS) have gained popularity due to their capability to model long sequences of highly non-linear and stochastic data effectively. However, the evolution of TSFAs for predicting agrometeorological parameters pivots around one-step-ahead forecasting, which often overestimates the performance metrics defined for validating forecast capabilities of potential TSFAs. Hence, this paper attempts to evaluate and compare the performance of different machine learning (ML) and deep learning (DL) based TSFAs under one-step and multi-step-ahead forecast scenarios, thereby estimating the generalization capabilities of TSFA models over unseen data. The data used in this study are collected from an Automatic Weather Station (AWS), sampled at an interval of 15 min, and range over one month. Temperature (T) and Humidity (H) observations from the AWS are further converted into univariate, supervised time-series diurnal data profiles. Finally, walk-forward validation is used to evaluate recursive one-step-ahead forecasts until the desired prediction horizon is achieved. The results show that the Seasonal Auto-Regressive Integrated Moving Average (SARIMA) and SVR models outperform their DL-based counterparts in one-step and multi-step ahead settings with a fixed forecast horizon. This work aims to present a baseline comparison between different TSFAs to assist the process of model selection and facilitate rapid ahead-of-time forecasting for end-user applications.<\/jats:p>","DOI":"10.3390\/s21072430","type":"journal-article","created":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T10:44:01Z","timestamp":1617273841000},"page":"2430","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":56,"title":["Time Series Forecasting of Univariate Agrometeorological Data: A Comparative Performance Evaluation via One-Step and Multi-Step Ahead Forecasting Strategies"],"prefix":"10.3390","volume":"21","author":[{"given":"Saurabh","family":"Suradhaniwar","sequence":"first","affiliation":[{"name":"Centre of Studies in Resources Engineering, Indian Institute of Technology Bombay, Mumbai 400076, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2158-2540","authenticated-orcid":false,"given":"Soumyashree","family":"Kar","sequence":"additional","affiliation":[{"name":"Centre of Studies in Resources Engineering, Indian Institute of Technology Bombay, Mumbai 400076, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Surya S.","family":"Durbha","sequence":"additional","affiliation":[{"name":"Centre of Studies in Resources Engineering, Indian Institute of Technology Bombay, Mumbai 400076, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adinarayana","family":"Jagarlapudi","sequence":"additional","affiliation":[{"name":"Centre of Studies in Resources Engineering, Indian Institute of Technology Bombay, Mumbai 400076, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,4,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/0169-2070(94)90052-3","article-title":"Economic forecasting in agriculture","volume":"10","author":"Allen","year":"1994","journal-title":"Int. J. Forecast."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1016\/S0925-2312(03)00372-2","article-title":"Financial time series forecasting using support vector machines","volume":"55","author":"Kim","year":"2003","journal-title":"Neurocomputing"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1016\/j.ijforecast.2006.01.001","article-title":"25 years of time series forecasting","volume":"22","author":"Hyndman","year":"2006","journal-title":"Int. J. Forecast."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1016\/j.envsoft.2018.06.004","article-title":"Time series analysis with explanatory variables: A systematic literature review","volume":"107","author":"Oliveira","year":"2018","journal-title":"Environ. Model. Softw."},{"key":"ref_5","unstructured":"Kang, Y., Hyndman, R.J., and Li, F. (2018). Efficient Generation of Time Series with Diverse and Controllable Characteristics (No. 15\/18), Department of Econometrics and Business Statistics, Monash University."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"794","DOI":"10.1016\/j.jhydrol.2018.02.060","article-title":"Estimation of daily reference evapotranspiration (ETo) using artificial intelligence methods: Offering a new approach for lagged ETo data-based modeling","volume":"559","author":"Mehdizadeh","year":"2018","journal-title":"J. Hydrol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1016\/j.compag.2018.07.008","article-title":"Survey of different data-intelligent modeling strategies for forecasting air temperature using geographic information as model predictors","volume":"152","author":"Sanikhani","year":"2018","journal-title":"Comput. Electron. Agric."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1016\/j.compag.2019.03.022","article-title":"Solar radiation estimation methods using ANN and empirical models","volume":"160","author":"Antonopoulos","year":"2019","journal-title":"Comput. Electron. Agric."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"105636","DOI":"10.1016\/j.compag.2020.105636","article-title":"Development of a linear based stochastic model for daily soil temperature prediction: One step forward to sustainable agriculture","volume":"176","author":"Zeynoddin","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"3010","DOI":"10.1016\/j.sigpro.2007.05.015","article-title":"Adaptive model selection for time series prediction in wireless sensor networks","volume":"87","author":"Santini","year":"2007","journal-title":"Signal. Process."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1016\/j.compag.2015.08.011","article-title":"Wireless sensor networks for agriculture: The state-of-the-art in practice and future challenges","volume":"118","author":"Ojha","year":"2015","journal-title":"Comput. Electron. Agric."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Bhandari, S., Bergmann, N., Jurdak, R., and Kusy, B. (2017). Time Series Data Analysis of Wireless Sensor Network Measurements of Temperature. Sensors, 17.","DOI":"10.3390\/s17061221"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"894","DOI":"10.1016\/j.compeleceng.2018.01.013","article-title":"Trust based data prediction, aggregation and reconstruction using compressed sensing for clustered wireless sensor networks","volume":"72","author":"Gilbert","year":"2018","journal-title":"Comput. Electr. Eng."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Makridakis, S., Spiliotis, E., and Assimakopoulos, V. (2018). Statistical and Machine Learning forecasting methods: Concerns and ways forward. PLoS ONE, 13.","DOI":"10.1371\/journal.pone.0194889"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1016\/j.compag.2017.11.038","article-title":"Assessing the potential of data-driven models for estimation of long-term monthly temperatures","volume":"144","author":"Mehdizadeh","year":"2018","journal-title":"Comput. Electron. Agric."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.compag.2019.03.030","article-title":"Data splitting strategies for improving data driven models for reference evapotranspiration estimation among similar stations","volume":"162","author":"Shiri","year":"2019","journal-title":"Comput. Electron. Agric."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1111\/j.1467-9892.1982.tb00339.x","article-title":"Testing for Gaussianity and Linearity of a Stationary Time Series","volume":"3","author":"Hinich","year":"1982","journal-title":"J. Time Ser. Anal."},{"key":"ref_18","unstructured":"Hansen, P.R., and Timmermann, A. (2021, January 08). Choice of Sample Split in Out-of-Sample Forecast Evaluation. Available online: http:\/\/hdl.handle.net\/1814\/21454."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/S0304-4076(95)01749-6","article-title":"Fractionally integrated generalized autoregressive conditional heteroskedasticity","volume":"74","author":"Baillie","year":"1996","journal-title":"J. Econ."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2861","DOI":"10.1016\/j.neucom.2006.06.015","article-title":"Methodology for long-term prediction of time series","volume":"70","author":"Sorjamaa","year":"2007","journal-title":"Neurocomputing"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Weigend, A.S. (2018). Time Series Prediction: Forecasting the Future and Understanding the Past, Routledge.","DOI":"10.4324\/9780429492648"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1016\/0925-2312(95)00020-8","article-title":"A comparison of artificial neural network and time series models for forecasting commodity prices","volume":"10","author":"Kohzadi","year":"1996","journal-title":"Neurocomputing"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1007\/s11222-009-9153-8","article-title":"Estimation of prediction error by using K-fold cross-validation","volume":"21","author":"Fushiki","year":"2011","journal-title":"Stat. Comput."},{"key":"ref_24","unstructured":"Lim, B., and Zohren, S. (2004). Time-series forecasting with deep learning: A survey. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Dabrowski, J.J., Zhang, Y., and Rahman, A. (2020). ForecastNet: A Time-Variant Deep Feed-Forward Neural Network Architecture for Multi-step-Ahead Time-Series Forecasting. International Conference on Neural Information Processing, Springer.","DOI":"10.1007\/978-3-030-63836-8_48"},{"key":"ref_26","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2020). Attention is all you need. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1007\/s10044-020-00898-1","article-title":"Deep learning-based effective fine-grained weather forecasting model","volume":"24","author":"Hewage","year":"2021","journal-title":"Pattern Anal. Appl."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1717","DOI":"10.1175\/BAMS-D-15-00308.1","article-title":"The Weather Research and Forecasting Model: Overview, System Efforts, and Future Directions","volume":"98","author":"Powers","year":"2017","journal-title":"Bull. Am. Meteorol. Soc."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"105728","DOI":"10.1016\/j.compag.2020.105728","article-title":"Multi-step ahead forecasting of daily reference evapotranspiration using deep learning","volume":"178","author":"Ferreira","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1016\/j.neucom.2019.11.060","article-title":"Multistage attention network for multivariate time series prediction","volume":"383","author":"Hu","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Wu, Z., Pan, S., Long, G., Jiang, J., Chang, X., and Zhang, C. (2020, January 23\u201327). Connecting the dots: Multivariate time series forecasting with graph neural networks. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery Data Mining, Virtual Event, CA, USA.","DOI":"10.1145\/3394486.3403118"},{"key":"ref_32","first-page":"914","article-title":"Spatial-Temporal Synchronous Graph Convolutional Networks: A New Framework for Spatial-Temporal Network Data Forecasting","volume":"34","author":"Song","year":"2020","journal-title":"Proc. Conf. AAAI Artif. Intell."},{"key":"ref_33","unstructured":"Moody, J.E., and Saffell, M. (2021, March 18). Reinforcement Learning for Trading. Available online: https:\/\/papers.nips.cc\/paper\/1998\/file\/4e6cd95227cb0c280e99a195be5f6615-Paper.pdf."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"113820","DOI":"10.1016\/j.eswa.2020.113820","article-title":"Multi-DQN: An ensemble of Deep Q-learning agents for stock market forecasting","volume":"164","author":"Carta","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"12633","DOI":"10.1111\/exsy.12633","article-title":"A hybrid model for financial time-series forecasting based on mixed methodologies","volume":"38","author":"Luo","year":"2021","journal-title":"Expert Syst."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1081","DOI":"10.1002\/for.2677","article-title":"On the forecasting of high-frequency financial time series based on ARIMA model improved by deep learning","volume":"39","author":"Li","year":"2020","journal-title":"J. Forecast."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"113775","DOI":"10.1016\/j.eswa.2020.113775","article-title":"Multiple breaks detection in financial interval-valued time series","volume":"164","author":"Cappelli","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"113237","DOI":"10.1016\/j.eswa.2020.113237","article-title":"Developing a deep learning framework with two-stage feature selection for multivariate financial time series forecasting","volume":"148","author":"Niu","year":"2020","journal-title":"Expert Syst. Appl."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1016\/j.tplants.2015.10.015","article-title":"Machine learning for high-throughput stress phenotyping in plants","volume":"21","author":"Singh","year":"2016","journal-title":"Trends Plant Sci."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/j.compag.2016.11.011","article-title":"Daily reference evapotranspiration estimates by artificial neural networks technique and empirical equations using limited input climate variables","volume":"132","author":"Antonopoulos","year":"2017","journal-title":"Comput. Electron. Agric."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13007-020-00680-8","article-title":"Automated discretization of \u2018transpiration restriction to increasing VPD\u2019 features from outdoors high-throughput phenotyping data","volume":"16","author":"Kar","year":"2020","journal-title":"Plant Methods"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1633","DOI":"10.5194\/hess-11-1633-2007","article-title":"Updated world map of the K\u00f6ppen-Geiger climate classification","volume":"11","author":"Peel","year":"2007","journal-title":"Hydrol. Earth Syst. Sci."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"511","DOI":"10.1007\/s10021-019-00416-3","article-title":"Dynamics of Ecosystem Water Use Efficiency in Citrus Orchards of Central India Using Eddy Covariance and Landsat Measurements","volume":"23","author":"Peddinti","year":"2019","journal-title":"Ecosystems"},{"key":"ref_44","unstructured":"Taieb, S.B., and Hyndman, R.J. (2012). Recursive and Direct Multi-Step Forecasting: The Best of Both Worlds, Department of Econometrics and Business Statistics, Monash University."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1016\/j.ijforecast.2004.08.004","article-title":"Non-parametric direct multi-step estimation for forecasting economic processes","volume":"21","author":"Chevillon","year":"2005","journal-title":"Int. J. Forecast."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1078","DOI":"10.1016\/j.apenergy.2018.12.042","article-title":"Day-ahead building-level load forecasts using deep learning vs. traditional time-series techniques","volume":"236","author":"Cai","year":"2019","journal-title":"Appl. Energy"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1109\/TNNLS.2015.2411629","article-title":"A bias and variance analysis for multistep-ahead time series forecasting","volume":"27","author":"Taieb","year":"2015","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_48","unstructured":"Fan, J., and Yao, Q. (2008). Nonlinear Time Series: Nonparametric and Parametric Methods, Springer Science & Business Media."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"7067","DOI":"10.1016\/j.eswa.2012.01.039","article-title":"A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition","volume":"39","author":"Bontempi","year":"2012","journal-title":"Expert Syst. Appl."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Akanbi, A., and Masinde, M. (2020). A Distributed Stream Processing Middleware Framework for Real-Time Analysis of Heterogeneous Data on Big Data Platform: Case of Environmental Monitoring. Sensors, 20.","DOI":"10.3390\/s20113166"},{"key":"ref_51","unstructured":"Box, G.E., Jenkins, G.M., Reinsel, G.C., and Ljung, G.M. (2015). Time Series Analysis: Forecasting and Control, John Wiley & Sons."},{"key":"ref_52","unstructured":"Hyndman, R.J., Athanasopoulos, G., Bergmeir, C., Caceres, G., Chhay, L., O\u2019Hara-Wild, M., Petropoulos, F., Razbash, S., Wang, E., and Yasmeen, F. (2021, January 08). Forecast: Forecasting Functions for Time Series and Linear Models. Available online: https:\/\/researchportal.bath.ac.uk\/en\/publications\/forecast-forecasting-functions-for-time-series-and-linear-models."},{"key":"ref_53","first-page":"155","article-title":"Support vector regression machines","volume":"9","author":"Drucker","year":"1997","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_54","unstructured":"Koskela, T., Lehtokangas, M., Saarinen, J., and Kaski, K. (1996, January 16\u201319). Time series prediction with multilayer perceptron, FIR and Elman neural networks. Proceedings of the 1996 World Congress on Neural Networks, Bochum, Germany."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1109\/72.279188","article-title":"Recurrent neural networks and robust time series prediction","volume":"5","author":"Connor","year":"1994","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_56","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_57","doi-asserted-by":"crossref","first-page":"170","DOI":"10.2307\/1165320","article-title":"The Kruskal-Wallis test and stochastic homogeneity","volume":"23","author":"Vargha","year":"1998","journal-title":"J. Educ. Behav. Stat."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"1169","DOI":"10.21105\/joss.01169","article-title":"Scikit-posthocs: Pairwise multiple comparison tests in Python","volume":"4","author":"Terpilowski","year":"2019","journal-title":"J. Open Source Softw."},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/380995.380999","article-title":"Support vector machines: Hype or hallelujah?","volume":"2","author":"Bennett","year":"2000","journal-title":"ACM SIGKDD Explor. Newslett."},{"key":"ref_60","doi-asserted-by":"crossref","unstructured":"Gers, F.A., Eck, D., and Schmidhuber, J. (2002). Applying LSTM to time series predictable through time-window approaches. Neural Nets WIRN Vietri-01, Springer.","DOI":"10.1007\/978-1-4471-0219-9_20"},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"594","DOI":"10.1080\/07474938.2010.481556","article-title":"An Empirical Comparison of Machine Learning Models for Time Series Forecasting","volume":"29","author":"Ahmed","year":"2010","journal-title":"Econ. Rev."},{"key":"ref_62","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1016\/j.ijforecast.2019.03.015","article-title":"A brief history of forecasting competitions","volume":"36","author":"Hyndman","year":"2020","journal-title":"Int. J. Forecast."},{"key":"ref_63","doi-asserted-by":"crossref","first-page":"482","DOI":"10.1016\/j.neucom.2013.09.010","article-title":"Multi-step-ahead time series prediction using multiple-output support vector regression","volume":"129","author":"Bao","year":"2014","journal-title":"Neurocomputing"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/7\/2430\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T13:56:00Z","timestamp":1760363760000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/7\/2430"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,1]]},"references-count":63,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2021,4]]}},"alternative-id":["s21072430"],"URL":"https:\/\/doi.org\/10.3390\/s21072430","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,1]]}}}