Assessing the Best Gap-Filling Technique for River Stage Data Suitable for Low Capacity Processors and Real-Time Application Using IoT
<p>Control points on the main Guadalquivir’s river axis: E10 (Pedro Marín), A08_101 (Mengibar), E25 (Marmolejo), E78 (El Carpio), E79 (Villafranca), I11 (Fuente Palmera), E53 (Peñaflor), and E60 (Alcalá del Río).</p> "> Figure 2
<p>A17 Genil-Écija checkpoint booth with satellite dish for satellite connection with Hispasat 1ª, SAIH equipment (SAINCO/Telvent) and the Vegaplus 62 radar sensor.</p> "> Figure 3
<p>Scheme of a conventional multilayer perceptron.</p> "> Figure 4
<p>Block diagram followed in Test I.</p> "> Figure 5
<p>Block diagram followed in Test II.</p> "> Figure 6
<p>Dynamic seed NARNN validation algorithm.</p> "> Figure 7
<p>Block diagram of the SAIH system (SAINCO/Telvent) and the equipment developed (green).</p> "> Figure 8
<p>Equipment implemented for the test at the A17 Genil-Écija control point of the SAIH system of the Guadalquivir river.</p> "> Figure 9
<p>The new equipment coupled to the SAIH system.</p> "> Figure 10
<p>(<b>a</b>) Comparison of the three gap-filling methods: RBFs, Cubic spline and mono layer perceptron (50 50 5), (80 10 10). (<b>b</b>) Details of interpolations.</p> "> Figure 11
<p>Data obtained (every 15 mins from the A17 Genil-Écija control point), (<b>a</b>) with the equipment developed and (<b>b</b>) with those from the SAIH of the Guadalquivir river.</p> "> Figure 12
<p>Resolution of the dynamic NARNN as a function of the selected time interval and the percentage of data used for validation.</p> "> Figure 13
<p>Resolution of the dynamic NARNN as a function of the selected cadence and the lag (or delay) used in the NARNN feedback.</p> ">
Abstract
:1. Introduction
2. Materials and Methods
2.1. Study Area and Data Source for Data Correction
2.2. Control Point Used to Test the Alternative Pre-Validation System Developed
2.3. Gap-Filling Techniques
2.3.1. Cubic Splines
2.3.2. Radial Basis Functions
2.3.3. Multilayer Perceptrons
2.4. Gap Filling Techniques Used
2.4.1. Test Type I (Scattered Gaps)
2.4.2. Test Type II (Multiple Gaps)
2.5. Using a NARNN with Dynamic Seed
2.6. Alternative Electronic Equipment Developed for IoT Communication
- ABB CONTROL model 1SVR011718R2500 galvanic isolator [59] powered at 24 V DC, with input and outputs in the 4–20 mA range
- Arduino DUE module with a 32-bit Atmel SAM3 × 8E ARM Cortex-M3 CPU microcontroller [60], with a 12-bit analog/digital converter (A/D) and 0–3.3 V measurement range
- Arduino DUE also has a USB connection for a virtual RS232C port through which it obtains power
- This microcontroller has several input/output ports, it will be connected to the memory module (micro SD) with the serial peripheral interface (SPI) protocol and with the clock-calendar module with the inter-integrated circuit (I2C) protocol. In both cases, the signal voltage will be 3.3 V
- Precision resistor of 165 Ω, 0.25 W, ± 0.1% precision and ± 15 ppm/° C, [61], to go from 4–20 mA current levels to voltages between 0.66 V and 3.3 V, (V = IR)
- Ethernet module with a micro SD card socket [62], compatible with 3.3 V level signals, and with a W5100 Ethernet controller for local area network (LAN) communications. For the configuration that has been used, it only requires an SPI connection to access the micro SD card, which is used to record the data including the date and time they were acquired
- ChronoDot Real Time Clock (RTC) module [63], which is a temperature compensated calendar clock based on the DS3231SN chip with a drift of only ± 2 pmm, (1 min per year). It includes a CR1632 lithium battery, which gives it autonomy for about 8 years, being compatible with I2C signals of level 3.3 V
- Single-phase inverter from 24 V DC to 230 V AC of 300 W model A301-300W-24 [64] with square wave output at 50 Hz, ideal for supplying current to the power supply of a laptop
- Huawei 4G USB Modem model ES3372 [65] for internet connection
- Laptop with i7 processor, 8GB of RAM, Windows 10 and Matlab 2018b
2.6.1. Calibration of the Developed Equipment
2.6.2. Implementation in LCPs
2.6.3. Using Arduino
2.6.4. Use of Raspberry Pi 3
2.7. Previous Simulation in Matlab
2.8. Methods Used for IoT Connection
3. Results
3.1. Test I
3.2. Test II
3.3. Results of the Use of Boards Based on Arduino and Raspberry Pi 3
3.3.1. Test III
3.3.2. Test IV
3.4. Alternative Pre-Validation System with IoT: Analysis of the Data of the Tests Carried Out in the Control Point A17 Genil-Écija
3.5. Alternative Pre-Validation System with IoT: Quantification of the Maximum Resolution of the Dynamic NARNN Based on its Configuration Parameters
3.6. Alternative Pre-Validation System with IoT. Computational Cost of Real-Time Pre-Validations
4. Conclusions
Author Contributions
Funding
Acknowledgments
Conflicts of Interest
References
- Coulibaly, P.; Dibike, Y.B.; Anctil, F. Downscaling Precipitation and temperature with temporal neural networks. J. Hydrometeorol. 2005, 6, 483–496. [Google Scholar] [CrossRef]
- IPCC Part A: Global and Sectoral Aspects. (Contribution of Working Group II to the Fifth Assessment Report of the Intergovernmental Panel on Climate Change). Available online: https://www.ipcc.ch/pdf/assessment-report/ar5/wg2/WGIIAR5-FrontMatterA_FINAL.pdf (accessed on 24 October 2020).
- López-Lineros, M.; Estévez, J.; Giráldez, J.V.; Madueño, A. A new quality control procedure based on non-linear autoregressive neural network for validating raw river stage data. J. Hydrol. 2014, 510, 103–109. [Google Scholar] [CrossRef]
- López, M.; Madueño, A.; Estévez, J.; Giráldez, J.V.; Eduardo, A.; Barros, D.; Miguel, P.; Fernandes, F. 2 539 407. Available online: http://www.oepm.es/pdf/ES/0000/000/02/53/94/ES-2539407_B2.pdf (accessed on 24 October 2020).
- Estévez, J.; Gavilán, P.; García-Marín, A.P.; Zardi, D. Detection of spurious precipitation signals from automatic weather stations in irrigated areas. Int. J. Climatol. 2015, 35, 1556–1568. [Google Scholar] [CrossRef]
- Estévez, J.; Bellido-Jiménez, J.A.; Liu, X.; García-Marín, A.P. Monthly precipitation forecasts using wavelet neural networks models in a semiarid environment. Water 2020, 12, 1909. [Google Scholar] [CrossRef]
- Khalil, M.; Panu, U.; Lennox, W. Groups and neural networks based streamflow data infilling procedures. J. Hydrol. 2001, 241, 153–176. [Google Scholar] [CrossRef]
- Beauchamp, J.J.; Downing, D.J.; Railsback, S.F. Comparison of regression and time-series methods for synthesizing missing streamflow records. J. Am. Water Resour. Assoc. 1989, 25, 961–975. [Google Scholar] [CrossRef]
- Gyau-Boakye, P.; Schultz, G.A. Filling gaps in runoff time series in West Africa. Hydrol. Sci. J. 1994, 39, 621–636. [Google Scholar] [CrossRef]
- Yung, S.K.; Clarke, D.W. Local Sensor validation. Meas. Control 1989, 22, 132–141. [Google Scholar] [CrossRef]
- Yang, J.C.-Y.; Clarke, D.W. A self-validating thermocouple. IEEE Trans. Control Syst. Technol. 1997, 5, 239–253. [Google Scholar] [CrossRef]
- Tsang, K.M. Sensor data validation using gray models. ISA Trans. 2003, 42, 9–17. [Google Scholar] [CrossRef]
- Ju-Long, D. Control problems of grey systems. Syst. Control Lett. 1982, 1, 288–294. [Google Scholar] [CrossRef]
- Bennis, S.; Berrada, F.; Kang, N. Improving single-variable and multivariable techniques for estimating missing hydrological data. J. Hydrol. 1997, 191, 87–105. [Google Scholar] [CrossRef]
- Quevedo, J.; Puig, V.; Cembrano, G.; Blanch, J.; Aguilar, J.; Saporta, D.; Benito, G.; Hedo, M.; Molina, A. Validation and reconstruction of flow meter data in the Barcelona water distribution network. Control Eng. Pract. 2010, 18, 640–651. [Google Scholar] [CrossRef] [Green Version]
- Quevedo, J.; Chen, H.; Cugueró, M.À.; Tino, P.; Puig, V.; García, D.; Sarrate, R.; Yao, X. Combining learning in model space fault diagnosis with data validation/reconstruction: Application to the Barcelona water network. Eng. Appl. Artif. Intell. 2014, 30, 18–29. [Google Scholar] [CrossRef]
- Gregory, J.A. Shape preserving spline interpolation. Comput. Des. 1986, 18, 53–57. [Google Scholar] [CrossRef] [Green Version]
- Dontchev, A.L. Best interpolation in a strip. J. Approx. Theory 1993, 73, 334–342. [Google Scholar] [CrossRef] [Green Version]
- Bastian-Walther, M.; Schmidt, J.W. Range restricted interpolation using Gregory’s rational cubic splines. J. Comput. Appl. Math. 1999, 103, 221–237. [Google Scholar] [CrossRef] [Green Version]
- Kouibia, A.; Pasadas, M.; Rodríguez, M.L. Optimization of parameters for curve interpolation by cubic splines. J. Comput. Appl. Math. 2011, 235, 4187–4198. [Google Scholar] [CrossRef] [Green Version]
- Faris, A.K.; Yahya, Z.R.; Rusli, N.; Rusdi, N. Rational Cubic Spline for Preserving the Positivity of 3D Positive Data. In Proceedings of the 2nd International Conference on Mathematics, Engineering and Industrial Applications, Songkhla, Thailand, 10–12 August 2016; Volume 1775. [Google Scholar] [CrossRef] [Green Version]
- Samreen, S.; Sarfraz, M.; Hussain, M.Z. A quadratic trigonometric spline for curve modeling. PLoS ONE 2019, 14, 1–17. [Google Scholar] [CrossRef] [PubMed]
- Liu, Z.; Xiao, K.; Liu, X.; Jiang, P. Local Point Control of a New Rational Quartic Interpolating Spline. In Proceedings of the 6th International Conference on Simulation and Modeling Methodologies, Technologies and Applications, Lisbon, Portugal, 29–31 July 2016; pp. 165–171. [Google Scholar] [CrossRef]
- Liu, G.R. Meshfree Methods Moving Beyond the Finite Element Method, 2nd ed.; CRC Press: London, UK, 2010. [Google Scholar]
- Wendland, H. Scattered Data Approximation; Cambridge University Press: Cambridge, UK, 2004. [Google Scholar]
- Fedoseyev, A. Radial Basics Functions. Available online: https://web.archive.org/web/20170704000739/http://www.rbf-pde.org/index.html (accessed on 24 October 2020).
- The MathWorks Inc. Interpolation with Radial Basics Functions. Available online: https://www.mathworks.com/content/dam/mathworks/mathworks-dot-com/moler/interp.pdf (accessed on 24 October 2020).
- Farfield Technology Interpolation with Radial Basics Function. Available online: http://www.farfieldtechnology.com/products/toolbox/theory/rbffaq.html (accessed on 24 October 2020).
- Chen, W.; He, J.H. A Study on Radial basis function and quasi-monte carlo methods. Int. J. Nonlinear Sci. Numer. Simul. 2000, 1, 337–342. [Google Scholar] [CrossRef] [Green Version]
- Sarra, S.A.; Kansa, E.J. Multiquadric radial basis function approximation methods for the numerical solution of partial differential equations. Adv. Comput. Mech. 2009, 2, 2009. [Google Scholar]
- French, M.N.; Krajewski, W.F.; Cuykendall, R.R. Rainfall forecasting in space and time using a neural network. J. Hydrol. 1992, 137, 1–31. [Google Scholar] [CrossRef]
- Abrahart, R.; Kneale, P.E.; See, L.M. Neural Networks for Hydrological Modelling; Taylor & Francis: Oxfordshire, UK, 2004. [Google Scholar]
- Coutinho, E.R.; da Silva, R.M.; Madeira, J.G.F.; Coutinho, P.R.D.O.D.S.; Boloy, R.A.M.; Delgado, A.R.S. Application of artificial neural networks (ANNs) in the gap filling of meteorological time series. Rev. Bras. Meteorol. 2018, 33, 317–328. [Google Scholar] [CrossRef]
- Wanderley, H.S.; De Amorim, R.F.C.; Carvalho, F.O. Variabilidade espacial e preenchimento de falhas de dados pluviométricos para o estado de Alagoas. Rev. Bras. Meteorol. 2012, 27, 347–354. [Google Scholar] [CrossRef] [Green Version]
- Olcese, L.E.; Palancar, G.G.; Toselli, B.M. A method to estimate missing AERONET AOD values based on artificial neural networks. Atmos. Environ. 2015, 113, 140–150. [Google Scholar] [CrossRef]
- Bustami, R.; Bessaih, N.; Bong, C.; Suhaili, S. Artificial neural network for precipitation and water level predictions of bedup river. IAENG Int. J. Comput. Sci. 2007, 34, 228–233. [Google Scholar]
- Depiné, H.; Castro, N.M.D.R.; Pinheiro, A.; Pedrollo, O.C.; Depin, H. Preenchimento de falhas de dados horários de precipitação utilizando redes neurais artificiais. Rev. Bras. Recur. Hídricos 2014, 19, 51–63. [Google Scholar] [CrossRef]
- Gimenez, D.F.S.; Nery, J.T. Aplicação das redes neurais artificiais no preenchimento de dados diários de chuva no estado de São Paulo. Desafios Geogr. Física Front. Conhecimento 2017, 1, 1747–1755. [Google Scholar] [CrossRef] [Green Version]
- Binoti, H.B. De Falhas De Precipitação Mensal Na Região Serrana Do Espírito Santo. Available online: http://www.ppegeo.igc.usp.br/index.php/GEOSP/article/download/9971/9259 (accessed on 24 October 2020).
- Bonfante, A.G.; Ventura, T.M.; de Oliveira, A.G.; Marques, H.O.; Oliveira, R.S.; Martins, C.A.; de Figueiredo, J.M. Uma abordagem computacional para preenchimento de falhas em dados micro meteorológicos. Rev. Bras. Ciências Ambient. 2013, 27, 61–70. [Google Scholar]
- Yang, X. Nature-Inspired Metaheuristic Algorithms, 2nd ed.; Luniver Press: Somerset, UK, 2010; Volume 4. [Google Scholar]
- Ministerio para la Transición Ecológica, Confederación Hidrográfica del Guadalquivir. Available online: https://www.chguadalquivir.es/inicio (accessed on 24 October 2020).
- Vega Americas Inc. VEGAPULS 61 Radar Sensor for Continuous Level Measurement of Liquids. Available online: https://www.vega.com/en-us/products/product-catalog/level/radar/vegapuls-61 (accessed on 24 October 2020).
- Sainco/Telvent SAIH Equipment. Available online: https://www.energias-renovables.com/empresas/sainco (accessed on 24 October 2020).
- World Meteorological Organization WMO. Available online: https://www.wmo.int/pages/index_en.html (accessed on 24 October 2020).
- Taylor, J.W. Short-term electricity demand forecasting using double seasonal exponential smoothing. J. Oper. Res. Soc. 2003, 54, 799–805. [Google Scholar] [CrossRef]
- Farin, G. Curves and Surfaces for CAGD: A Practical Guide (The Morgan Kaufmann Series in Computer Graphics), 5th ed.; Morgan Kaufmann Publishers: Burlington, MA, USA, 2001. [Google Scholar]
- de Boor, C.R. A Practical guide to splines. Math. Comput. 1980, 34, 325. [Google Scholar] [CrossRef]
- Piegl, L.; Tiller, W. The NURBS Book; Springer: Berlin/Heidelberg, Germany, 1997. [Google Scholar]
- Rogers, D.F. An Introduction to NURBS With Historical Perspective; Morgan Kaufmann: Burlington, MA, USA, 2001. [Google Scholar]
- Press, W.H.; Teukolsky, S.A.; Wettering, W.T. Numerical Recipes in C: The Art of Scientific Computing; Foundation Book: Cambridge, UK, 2007. [Google Scholar]
- Kansa, E.J. Motivation for Using Radial Basis Functions to Solve PDEs. Available online: https://people.clarkson.edu/~gyao/kansa_rbf_pde.pdf (accessed on 24 October 2020).
- Rumelhart, D.E.; McClelland, J.L. Parallel Distributed Processing, Volume 1 Explorations in the Microstructure of Cognition: Foundations; MIT Press: Cambridge, MA, USA, 1986. [Google Scholar]
- Hornik, K.; Stinchcombe, M.; White, H. Multilayer feedforward networks are universal approximators. Neural Netw. 1989, 2, 359–366. [Google Scholar] [CrossRef]
- Estévez, J.; Gavilán, P.; Berengena, J. Sensitivity analysis of a Penman-Monteith type equation to estimate reference evapotranspiration in southern Spain. Hydrol. Process. 2009, 23, 3342–3353. [Google Scholar] [CrossRef]
- Madueño, A. Appendix. Available online: https://www.dropbox.com/sh/lzzjw113rv0asgy/AAAVY8WxuNoJlNSMr3iacf3za?dl=0 (accessed on 24 October 2020).
- Chirokov, A. Scattered Data Interpolation and Approximation Using Radial Base Functions. Available online: https://www.mathworks.com/matlabcentral/fileexchange/10056-scattered-data-interpolation-and-approximation-using-radial-base-functions (accessed on 24 October 2020).
- The MathWorks Inc. Nonlinear Autoregressive Neural Network With External Input. Available online: https://es.mathworks.com/help/deeplearning/ref/narxnet.html;jsessionid=b51cded74073ceac4cd276fae169 (accessed on 24 October 2020).
- Transfer Multisort Elektronik Sp. Z O.O. TEM Analog Signals Converter 1SVR011718R2500 ABB. Available online: https://www.tme.eu/gb/details/1svr011718r2500/measuring-conv-and-signal-isolators/abb/ (accessed on 24 October 2020).
- Arduino.cc Arduino DUE. Available online: https://www.arduino.cc/en/Main/arduinoBoardDue (accessed on 24 October 2020).
- Holco Metals Films Precision Resistances. Available online: https://www.hificollective.co.uk/components/holco_resistors.html (accessed on 24 October 2020).
- Arduino.cc Ethernet Shield. Available online: https://store.arduino.cc/arduino-ethernet-shield-2 (accessed on 24 October 2020).
- Macetech.com ChronoDot V2.1 High Precision RTC. Available online: http://macetech.com/store/index.php?main_page=product_info&cPath=5&products_id=8&zenid=69a08920187b1ae988e582c692fe7881 (accessed on 24 October 2020).
- AKOWA Electronics Co. Ltd. Available online: https://www.akowadcac.com/ (accessed on 24 October 2020).
- Huawei Technologies Co. Ltd. HUAWEI 4G Dongle E3372. Available online: https://consumer.huawei.com/en/routers/e3372/specs/ (accessed on 24 October 2020).
- Interworld Highway, L. HT Instruments HT8000 Portable Digital Process Calibrator. Available online: https://www.tequipment.net/HT-Instruments/HT8000/Voltage-Calibrators/ (accessed on 24 October 2020).
- Kerinin Arduino-Splines. Available online: https://github.com/kerinin/arduino-splines (accessed on 24 October 2020).
- Mai-Duy A Simple and Effective Preconditioner for Integrated-RBF-Based Cartesian-Grid Schemes. Available online: https://eprints.usq.edu.au/18393/ (accessed on 24 October 2020).
- Arduino-SVM. Available online: https://github.com/radzilu/Arduino-SVM (accessed on 24 October 2020).
- Neuroduino. Available online: https://github.com/t3db0t/Neuroduino (accessed on 24 October 2020).
- Yang, W.Y.; Cao, W.; Chung, T.-S. Applied Numerical Methods Using MATLAB; John Wiley and Sons: Hoboken, NJ, USA, 2005. [Google Scholar]
- Dropbox Inc. Dropbox. Available online: https://www.dropbox.com/ (accessed on 24 October 2020).
- LogMeIn. Available online: https://www.logmein.com (accessed on 24 October 2020).
Consumption (Watts) | Duration (Number of Times) | |||||||
---|---|---|---|---|---|---|---|---|
PC | Raspberry Pi (RPi) | Arduino DUE | Arduino UNO | RPi/PC | Arduino DUE/PC | Arduino UNO/PC | Arduino DUE/Rpi | Arduino UNO/Rpi |
220 | 1.8 | 0.8 | 0.4 | 122 | 220 | 550 | 2 | 4.5 |
Flag | Type of Data |
---|---|
0 | Correct |
1 | None |
2 | No satellite connection |
3 | Out of range |
4 | Manual |
5 | Non-observed-change in time interval |
Board | Processor | Bits | MIPS | SO |
---|---|---|---|---|
Arduino UNO | ATMEGA328P-PU | 8 | 16 | NO |
Arduino DUE | SAM3 × 8E ARM Cortex-M3 | 32 | 84 | NO |
Raspberry PI 3 | Broadcom BCM2837 | 32 | 2441 | RASPBIAN |
SEE | ||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
n | m | p | m1 | q | Neurons | Spline (×10−2) | RBF_Lin (×10−2) | RBF_G (×10−2) | RBF_C (×10−2) | RBF_T (×10−2) | RBF_M (×10−2) | MLP (×10−2) |
300 | 10 | 80 | 10 | 8 | 50_50_5 | 1.32 | 1.46 | 3.96 | 1.76 | 1.66 | 1.46 | 3.58 |
300 | 10 | 80 | 30 | 24 | 50_50_5 | 10.5 | 5.01 | 8.30 | 8.90 | 7.63 | 5.01 | 7.75 |
300 | 10 | 80 | 13 | 10 | 50_50_5 | 2.01 | 2.78 | 6.69 | 4.33 | 3.60 | 2.78 | 1.84 |
p/n | 100 | 150 | 200 | 500 | 1000 | 5000 |
---|---|---|---|---|---|---|
0.05 | 0.623 | 0.642 | 0.771 | 0.89 | 0.972 | 1.03 |
0.10 | 0.71 | 0.872 | 0.948 | 0.99 | 1.09 | 1.06 |
0.25 | 0.914 | 0.955 | 1.11 | 1.14 | 1.11 | 1.11 |
0.50 | 0.99 | 0.998 | 1.08 | 1.13 | 1.06 | 1.13 |
0.75 | 1.06 | 1.06 | 1.07 | 1.09 | 1.15 | 1.04 |
* Bold font for MLP |
Board | Spline | RBF Lineal | RBF Gaussian | RBF Cubic | RBF Thin-Plate | RBF Muticuadrics | MLP (n = 5) |
---|---|---|---|---|---|---|---|
Arduino UNO | <2 s | <1 s | <3 s | <1s | <1s | <3s | <45 min |
Arduino DUE | <1 s | <1s | <1s | <1s | <1s | <1s | <8 min |
Raspberry PI 3 | <1 s | <1s | <1s | <1s | <1s | <1s | <1min |
p/n | 100 | 150 | 200 |
---|---|---|---|
0.05 | <8 min | <14 min | <21 min |
0.1 | <12 min | <18 min | <32 min |
0.25 | <17 min | <24 min | < 51 min |
Cadence (s) | n_Neurons | Delay | Percentage (%) | Resolution (cm) |
---|---|---|---|---|
60 | 1 | 1 | 25 | 9 |
60 | 1 | 1 | 35 | 9 |
60 | 1 | 11 | 25 | 9 |
60 | 1 | 21 | 95 | 7.5 |
60 | 1 | 26 | 25 | 8 |
60 | 1 | 30 | 95 | 5.5 |
Case | Cadence (s) | Percentage (%) | Time Cost (s) |
---|---|---|---|
1 | 50 | 0.25 | 23.1 |
2 | 55 | 0.25 | 24.5 |
3 | 55 | 0.35 | 26.1 |
4 | 60 | 0.25 | 20.0 |
5 | 60 | 0.35 | 28.3 |
6 | 60 | 0.45 | 27.5 |
Case | Cadence (s) | Percentage (%) | Time Cost (s) | Resolution (cm) |
---|---|---|---|---|
1 | 50 | 0.25 | 23.1 | 8.53 |
3 | 55 | 0.35 | 26.1 | 6.14 |
6 | 60 | 0.45 | 27.5 | 8.32 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Luna, A.M.; Lineros, M.L.; Gualda, J.E.; Giráldez Cervera, J.V.; Madueño Luna, J.M. Assessing the Best Gap-Filling Technique for River Stage Data Suitable for Low Capacity Processors and Real-Time Application Using IoT. Sensors 2020, 20, 6354. https://doi.org/10.3390/s20216354
Luna AM, Lineros ML, Gualda JE, Giráldez Cervera JV, Madueño Luna JM. Assessing the Best Gap-Filling Technique for River Stage Data Suitable for Low Capacity Processors and Real-Time Application Using IoT. Sensors. 2020; 20(21):6354. https://doi.org/10.3390/s20216354
Chicago/Turabian StyleLuna, Antonio Madueño, Miriam López Lineros, Javier Estévez Gualda, Juan Vicente Giráldez Cervera, and José Miguel Madueño Luna. 2020. "Assessing the Best Gap-Filling Technique for River Stage Data Suitable for Low Capacity Processors and Real-Time Application Using IoT" Sensors 20, no. 21: 6354. https://doi.org/10.3390/s20216354