Prediction of surface water quality of Allahabad and Varanasi inUTTAR PRADESH

International Research Journal of Engineering and Technology (IRJET) e-ISSN:2395-0056

Volume: 09 Issue: 08 | Aug 2022 www.irjet.net p-ISSN:2395-0072

Prediction of surface water quality of

inUTTAR PRADESH

Allahabad and Varanasi

Ambuj Verma1 , Dr. Anirudh Gupta2

1M.Tech. Student, Environmental Engineering, Institute of Engineering and Technology,Lucknow, Uttar Pradesh, India

2Assistant Professor, Civil Engineering Department, Institute of Engineering and Technology,Lucknow, Uttar Pradesh, India ***

Abstract - Surface Water quality is gradually deteriorate due to population growth and a faster rate of industrialization. Rivers in India are the country's primary source of water. Half of India's population, including two- thirds of the country's poor, lives in the Ganga River Basin, which is the most populous region in the world. This paper highlights the utility of statistical techniques for evaluating, interpreting complexdatasetsandrecognizingspatialdifferencesin water quality for effective management of riverwater quality. Time-series data and statistical analysis are used by the Autoregressive Integrated Moving Average (ARIMA)modeltounderstandthedataandforecastthe future. 6 water quality parameters Dissolved Oxygen, BOD, pH, Temperature, Electrical Conductivity and Total Coliform areanalyzed and predicted. In this work 4monitoringstationistakenforthepredictionanalysis inAllahabadandVaranasi,dataistakenfromtheCPCB. In this work ARIMA model is giving the better prediction of BOD, total coliform and conductivity in compare of other water quality parameter pH, temperature and DO. The max value for correlation coefficientfor Dissolved Oxygen, BOD, pH, Temperature, Electrical Conductivity and Total Coliform are respectively0.65,0.90,0.68,0.68,0.86and0.84

Key Words: ARIMA model, surface water quality prediction, Allahabad, Varanasi

1. INTRODUCTION

Since ancient times, the river Ganges has been reveredasoneofthemostsacredandholyriversinthe world.Sincethebeginningoftime,peoplehaverevered theGangesasoneofthemostholyandsacredriversin the world. The evaluationof river water quality is a critical elementintheassessmentof water resources. Thequalityofwaterthatisconsumeddefinesthebase lineofprotectionagainstmanydiseasesandinfections. The Ganga, with over 2,525 km long main-stemalong withhertributarieshasconstantlyprovidedmaterial,

Spiritualandculturalsustenancetomillionsofpeopleliving in and around its basin. The riverine water resources provide irrigation, drinking water, economical transportation, electricity, recreation and religious fulfilment, support to the aquatic ecosystem as well as livelihoods for many stakeholders. This river has both emotionalandspiritualvalueamongIndians.Thewaterof Gangacarriesreligioussentimentsandisconsideredasthe purestwaterwhichcanwashoffallthesinsofthehuman being. However, present study is carried out with an objectivetoassessthewaterqualityoftheGangawateratits descendent pointontheplainswhereit issupposedto be leastpolluted.TheriverGangesinIndiaisregardedasthe most holy and sacred rivers of the world by Hindus from timeimmemorial.BhagirathiisthesourcestreamofGanga. The river has been the focus of national and international interventionandstudyforpastseveraldecadestoidentify andestablishcausesandimpactofanthropogenicactivities onriverwaterquality.

1.1 Study Area

GangesRiver,GreatRiveroftheplainsofthenorthernIndian subcontinent.Althoughofficiallyaswellaspopularlycalled the Ganga in Hindi and in other Indian languages, internationally it is known by its conventional name, the Ganges.

Inthis paper wehave selectedfour locationsintheupper GangastretchintheUttarPradesh.Theselocationsaregiven below:1.GANGAATALLAHABADU/S(1046)

GANGAATALLAHABADD/S(1049)

GANGAATVARANASIU/S(ASSIGHAT)(1070)

GANGA AT VARANASI D/S (MALVIYA BRIDGE) (1071)

International Research Journal of Engineering and Technology (IRJET) e-ISSN:2395-0056

Volume: 09 Issue: 08 | Aug 2022 www.irjet.net p-ISSN:2395-0072

Figure 1; locationofstationinUttarPradesh

3. Materials and methods

Time series forecasting is one of many data analysis techniques that is often utilised in a variety of fields. One ofthemostsignificantandoftenused timeseries models is the autoregressive integrated moving average (ARIMA) model. ARIMA models can also implement a variety of exponential smoothing techniques. It is also referred as the Box-Jenkins methodology, which consists of a series of steps for identifying,estimatinganddiagnosingARIMAmodels withtimeseriesdata.ARIMAmodelshaveproventobe capableofproducingpreciseshort-termestimates.

Every component achieved are provided as a parameterinthismodel.ARIMA(p,d,q)isastandard notation in which the parameters are replaced by integer values to immediately indicate the ARIMA model being utilized. The ARIMAmodel'sparameters are(p)itdefinesthenumberoflaggedobservationsin themodel,alsoreferredasthelag order,(d)itcanbe understood as number of raw observations differenced, also referred as the degree of differencing, and (q) it is referred as the moving average order or the size of window in moving average.

InthisworkARIMA(1,1,1)isusedfortheprediction ofthesurfacewaterquality.

Mathematically,

laggederrorterm

Where,Ytisthepredictedvalue,Yt-1isthelag1oftheseries, β1isthecoefficientoflag1,αistheconstantortheintercept term,ϵtistherandomerroratt,ϵt-1isthe att-1,∅is thecoefficientoflaggederroratt-1.

a. Data source

The data used in this research and prediction is from the Central Pollution Control Board (CPCB). Monthly data is takenfromthe2016to2020forthe6surfacewaterquality parameteranditisarrangedintheMSExcelforthefurther calculation and the analysis. Dissolved oxygen, BOD, pH, temperature,electricalconductivity,andtotalcoliformare thenextparametersthatthisstudyismeasuring.

b. Data statistics

Thefollowingdataisobservedonthestations:-

Figure 2;StasticalanalysisofstationS1,S2,S3andS4

4. Result and discussion

Model performance was estimated by RMSE, MAPE, AIC and R2forthewaterqualityparametersDissolvedOxygen,BOD, pH,Temperature,ElectricalConductivityandTotalColiform. In summary, the ARIMA model performed significantly better prediction of temperature, total coliform and conductivity in compare of other water quality parameter pH, BOD and DO. Furthermore, different prediction performancecanbefoundforthefoursites.Theresultsfor monthly surface water quality are shown in Figure 3, 4, 5 and6.

International Research Journal of Engineering and Technology (IRJET) e-ISSN:2395-0056 Volume: 09 Issue: 08 | Aug 2022 www.irjet.net p-ISSN:2395-0072

Figure 3;PerformanceofARIMAmodelforstationS1

International Research Journal of Engineering and Technology (IRJET) e-ISSN:2395-0056 Volume: 09 Issue: 08 | Aug 2022 www.irjet.net p-ISSN:2395-0072

Figure 4; PerformanceofARIMAmodelforstationS2

ThepredictionofstationS3are–

International Research Journal of Engineering and Technology (IRJET) e-ISSN:2395-0056 Volume: 09 Issue: 08 | Aug 2022 www.irjet.net p-ISSN:2395-0072 © 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page1948

Figure 5; PerformanceofARIMAmodelforstationS3

International Research Journal of Engineering and Technology (IRJET) e-ISSN:2395-0056

ThepredictionofstationS4are–

Figure 6; PerformanceofARIMAmodelforstationS4

Volume: 09 Issue: 08 | Aug 2022 www.irjet.net p-ISSN:2395-0072 © 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page1949

International Research Journal of Engineering and Technology (IRJET) e-ISSN:2395-0056

Volume: 09 Issue: 08 | Aug 2022 www.irjet.net p-ISSN:2395-0072

5. CONCLUSIONS

The study displays prediction accuracy and error for all chosen sites for which analysis is conducted. The results shows for S1 station that this model is able to predict the bestvaluefortheconductivitywith0.83R2 valueandpHhas lower value 0.52 R2 . However, station S2 has highest efficiency0.86fortheconductivity andminvalue0.52for the pH. Station S3 has highest efficiency .75 for the total coliformandminvalue0.54forthetemperature.StationS4 hashighestefficiency.90fortheBODandminvalue0.55for thetemperatureandconductivity.

REFERENCES

[1] Bagla, P., Kumar, K., Sharma, N., & Sharma, R. (2021). Multivariate Analysis of Water Quality of Ganga River. Journal of The Institution of Engineers(India):SeriesB, 102(3),539-549.

[2] Bhutiani, R., Khanna, D. R., Kulkarni, D. B., & Ruhela, M. (2016). Assessment of Ganga river ecosystem at Haridwar, Uttarakhand, India with reference to Water Quality Indices. Applied Water Science, 6(2),107-113.

[3] Ighalo, J. O., Adeniyi, A. G., & Marques, G. (2021). Artificial intelligence for surface water quality monitoring and assessment: a systematic literature analysis. ModelingEarthSystemsandEnvironment, 7(2), 669-681.

[4] Zhang,Y.F.,Thorburn,P.J.,Xiang,W.,&Fitch,P.(2019). SSIM A deep learning approach for recovering missingtimeseriessensordata. IEEEInternetofThings Journal, 6(4),6618-6628.

[5] Ahmed,U.,Mumtaz,R.,Anwar,H.,Shah,A.A.,Irfan,R.,& García-Nieto, J. (2019). Efficient water quality prediction using supervised machine learning. Water, 11(11),2210.

Figure 7; Performance of ARIMA model for differentwaterqualityparameter

In conclusion, it is clear that the ARIMA model performs better in predicting BOD, total coliform, and conductivity than other water quality parameters such as pH, temperature, and DO. This complete analysis provides aninformation base to be usedbyregulatorsandpolicymakersforreconcilingthe competing interests in the Ganga river through delivering solutions to improve, monitor clean up, maintainwaterqualityandrestoreitsecosystem.

ACKNOWLEDGEMENT

Theauthorwishestoexpresshisparamountgratitude to Asst. Prof. Dr. Anirudh Gupta CED, IET Lucknow, their scholarly guidance and constructive feedback have been a source of inspiration and motivation to complete this paperand the Central Pollution Control Board (CPCB) for providing the essential data for conductingthispaper.

[6] Matta,G.,Kumar,A.,Nayak,A.,Kumar,P.,Kumar,A.,& Tiwari,A.K.(2020).Determinationofwaterqualityof Ganga River System in Himalayan region, referencing indexing techniques. Arabian Journal of Geosciences, 13(19),1-11.

[7] Hassan,M.M.,Hassan,M.M.,Akter,L.,Rahman,M.M., Zaman, S., Hasib, K. M & Mollick, S. (2021). Efficient PredictionofWaterQualityIndex(WQI)UsingMachine Learning Algorithms. Human-Centric Intelligent Systems, 1(3-4),86-97.

[8] Abdelmalik, K.W. (2016). Role of statistical remote sensing for Inland water quality parameters prediction. Egypt.J.RemoteSensingSpaceSci.21,154.

[9] Avila, R., Horn, B., Moriarty, E., Hodson, R., and Moltchanova, E. (2018). Evaluating statistical model performance in water quality prediction. J. Environ. Manage.206,910.

[10] Bedri, Z., Corkery, A., O’Sullivan, J.J., Deering, L.A., and Demeter, K. (2016). Evaluating a microbial water qualitypredictionmodelforbeachmanagementunder the revised EU Bathing Water Directive. J. Environ. Manage.167,49.

International Research Journal of Engineering and Technology (IRJET) e-ISSN:2395-0056

Volume: 09 Issue: 08 | Aug 2022 www.irjet.net p-ISSN:2395-0072

BIOGRAPHIES

Ambuj Verma is a student of Master of Technology, Environmental Engineering, Dept. of Civil Engineering, Institute of Engineering and Technology, Lucknow, Uttar Pradesh.

Dr.AnirudhGuptaisworking asAssistantProfessor,Dept.,of CivilEngineering in Institute of Engineering and Technology, Lucknow, Uttar Pradesh.

2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page1951