地下水為臺灣重要之水資源之一，過度使用地下水會引發海水入侵、地層下陷等諸多問題，最常見蓄水方法是使用地表水庫，然而，由於土地徵用、污染問題、蒸發或入滲消耗，過度仰賴地表水庫有時會出現問題，此外，在沿海等相對平坦的地區建設水庫會遇到許多限制。含水層儲蓄回抽 (aquifer storage and recovery，簡稱ASR) 其原理是將從地表收集豐水期的水將其注入地下含水層中進行儲存，以供未來需要時使用的儲水方式。進行鑽探本身費時費力，在所有地點進行顯然不可行，因此人工神經網路(ANN)是一個利用有限的資料推估整個範圍資料的一種方式。本研究的目的為利用ANN進行空間內插找出台灣適合進行ASR的可行場址，將座標與觀測井的直線距離作為人工神經網路的輸入參數，以流通係數數值與地下水水質作為輸出結果。人工神經網路結果顯示在2層隱藏層且每層神經元個數為16時有最好的預測效果 ，最後加入河川分布圖篩選台灣ASR優選場址，以確保廠址周圍具有水源，結果可供政府機構判斷適合ASR的場址。

Groundwater is one of Taiwan's important water resources. Excessive use of groundwater can lead to various problems such as salt water intrusion and land subsidence. The most common method of water storage is through surface water reservoirs. However, over-reliance on surface water reservoirs can sometimes pose problems due to land acquisition, pollution issues, evaporation, or infiltration. Additionally, constructing reservoirs in relatively flat areas, such as coastal regions, faces many restrictions. Aquifer Storage and Recovery (ASR) is a water storage method that involves collecting water from the surface during periods of abundance and injecting it into underground aquifers for storage, to be used in the future when needed. Drilling itself is time-consuming and labor-intensive, and it is obviously not feasible to conduct it in all locations. Therefore, artificial neural network (ANN) is a way to use limited data to estimate the entire range of data. The purpose of this study is to use ANN for spatial interpolation to identify feasible sites in Taiwan for ASR. The straight-line distance between coordinates and observation well locations is used as input parameters for the artificial neural network, with transmissivity values and groundwater quality as output results. The results from the artificial neural network indicate that the best predictive performance occurs with two hidden layers, each with 16 neurons. Finally, a river distribution map is incorporated to filter and select optimal ASR sites in Taiwan, ensuring that there is a water source around the selected locations. These results can be used by government agencies to determine suitable ASR sites.

[1] Alliance, W. R. O. N. (2007). Australian water resources 2005: a baseline assessment of water resources for the National Water Initiative. National Water Commission Australia, Canberra.
[2] Heywood, C. E., Griffith, J. M., & Lovelace, J. K. (2014). Simulation of Groundwater Flow in the" 1,500-foot" Sand and" 2000-foot" Sand with Scenarios to Mitigate Saltwater Migration in the '2000-foot" Sand of the Baton Rouge Area, Louisiana. (US Geological Survey Scientific Investigations Report No. 2013-5227). United States Department of the Interior, US Geological Survey. http://dx.doi.org/10.3133/sir20135227
[3] Borrok, D. M., Chen, J., Eldardiry, H., & Habib, E. (2018). A framework for incorporating the impact of water quality on water supply stress: An example from Louisiana, USA. JAWRA Journal of the American Water Resources Association, 54(1), 134-147. https://doi.org/10.1111/1752-1688.12597
[4] Thomas, D., Hook, J., Hoogenboom, G., Harrison, K., & Stooksbury, D. (2000). Drought management impacts on irrigation in southwest Georgia. In Proceedings of the 2000 ASAE Annual International Meeting (pp. 1-9). American Society of Agricultural Engineers.
[5] Liu, J., Rich, K., & Zheng, C. (2008). Sustainability analysis of groundwater resources in a coastal aquifer, Alabama. Environmental Geology, 54, 43-52. https://doi.org/10.1007/s00254-007-0791-x
[6] Konikow, L. F. (2013). Groundwater depletion in the United States (1900−2008) (U.S. Geological Survey Scientific Investigations Report No. 2013−5079). United States Geological Survey. http://pubs.usgs.gov/sir/2013/5079
[7] Eldardiry, H., Habib, E., & Borrok, D. M. (2016). Small-scale catchment analysis of water stress in wet regions of the U.S.: An example from Louisiana. Environmental Research Letters, 11(12), 1–10. https://doi.org/10.1088/1748-9326/aa51dc
[8] Budhu, M., & Adiyaman, I. B. (2010). Mechanics of land subsidence due to groundwater pumping. International Journal for Numerical and Analytical Methods in Geomechanics, 34(14), 1459-1478. https://doi.org/10.1002/nag.863
[9] Dokka, R. K. (2011). The role of deep processes in late 20th century subsidence of New Orleans and coastal areas of southern Louisiana and Mississippi. Journal of Geophysical Research: Solid Earth, 116(B6). https://doi.org/10.1029/2010JB008008
[10] Jones, C. E., An, K., Blom, R. G., Kent, J. D., Ivins, E. R., & Bekaert, D. (2016). Anthropogenic and geologic influences on subsidence in the vicinity of New Orleans, Louisiana. Journal of Geophysical Research: Solid Earth, 121(5), 3867–87. https://doi.org/10.1002/2015JB012636
[11] Agarwal, R., Garg, P. K., & Garg, R. D. (2013). Remote sensing and GIS based approach for identification of artificial recharge sites. Water Resources Management, 27, 2671-2689. https://doi.org/10.1007/s11269-013-0310-7
[12] Ross, A., & Hasnain, S. (2018). Correction to: Factors affecting the cost of managed aquifer recharge (MAR) schemes. Sustainable Water Resources Management, 4(2), 191. https://doi.org/10.1007/s40899-018-0243-7
[13] Water Resources Agency. (2023). Retrieved from https://www.wra.gov.tw/News.aspx?n=2882&sms=9087
[14] US National Research Council. (2019). Retrieved from https://www.trwd.com/aquifer-storage-may-become-the-next-big-player/
[15] CDM Federal Programs Corporation. (2017). FEMA ASR.Pdf. Retrieved from https://www.fema.gov/media-library/assets/documents/129691
[16] Sheng, Z., & Zhao, X. (2015). Special issue on managed aquifer recharge: powerful management tool for meeting water resources challenges. Journal of Hydrologic Engineering, 20(3), B2014001. https://doi.org/10.1061/(ASCE)HE.1943-5584.0001139
[17] Bouwer, H., Pyne, R., Brown, J., St, D., Germain, T. M., Morris, C. J., ... & Rycus, M. J. (2009). Design, Operation, and Maintenance for Sustainable Underground Storage Facilities. Denver, CO: Water Environment Research Foundation.
[18] Pyne, R. D. G. (2005). Aquifer storage recovery: A guide to groundwater recharge through wells (2nd ed.). ASR Press.
[19] Maria T. Gibson (2018). Estimating Aquifer Storage and Recovery (ASR) Regional and Local Suitability: A Case Study in Washington State, USA.
[20] Maliva, R. G. (2014). Economics of managed aquifer recharge. Water, 6(5), 1257-1279. https://doi.org/10.3390/w6051257
[21] Dillon, P., Pavelic, P., Page, D., Beringen, H., & Ward, J. (2009). Managed Aquifer Recharge. Waterlines Report Series.
[22] Kelly, B. P., Pickett, L. L., Hansen, C. V., & Ziegler, A. C. (2013). Simulation of groundwater flow, effects of artificial recharge, and storage volume changes in the Equus Beds aquifer near the city of Wichita, Kansas well field, 1935–2008. U.S. Geological Survey Scientific Investigations Report, 2013–5042. US Department of the Interior, US Geological Survey.
[23] Webb, M. (2015). Texas ASR Projects [PDF]. Retrieved from http://www.twdb.texas.gov/publications/reports/technical_notes/doc/TechnicalNote15-04.pdf.
[24] Bouwer, H. (2002). Artificial recharge of groundwater: hydrogeology and engineering. Hydrogeology Journal, 10, 121-142. https://doi.org/10.1007/s10040-001-0182-4
[25] Rahman, M. A., Rusteberg, B., Gogu, R. C., Ferreira, J. L., & Sauter, M. (2012). A new spatial multi-criteria decision support tool for site selection for implementation of managed aquifer recharge. Journal of Environmental Management, 99, 61-75. https://doi.org/10.1016/j.jenvman.2012.01.003
[26] Todd, D. K., & Mays, L. W. (1980). A new spatial multi-criteria decision support tool for site selection for implementation of managed aquifer recharge.
[27] Khan, S., Mushtaq, S., Hanjra, M. A., & Schaeffer, J. (2008). Estimating potential costs and gains from an aquifer storage and recovery program in Australia. Agricultural Water Management, 95(4), 477-488.
[28] (N.d.). Aquifer Storage May Become the next Big Player – Tarrant Regional Water District. https://www.trwd.com/aquifer-storage-may-become-the-next-big-player/
[29] Robert, G. M., & Missimer, T. M. (2010). Aquifer Storage and Recovery and Managed Aquifer Recharge Using Wells.
[30] Kimbler, O. K., Kazmann, R. G., & Whitehead, W. R. (1975). Cyclic storage of fresh water in saline aquifers.
[31] Ward, J. D., Simmons, C. T., & Dillon, P. J. (2008). Variable-density modelling of multiple-cycle aquifer storage and recovery (ASR): Importance of anisotropy and layered heterogeneity in brackish aquifers. Journal of Hydrology, 356(1-2), 93-105.
[32] 經濟部水資源局. (2000). ASR地下水補注與回用先趨研究計畫(二)-屏東昌隆ASR示範廠可行性規劃.
[33] 美商西圖工程顧問國際有限公司台灣分公司. (2002). ASR 地下水補注與回用先驅研究計畫(三)屏東昌隆 ASR 示範廠 ASR 井設置及初步循環操作測試. 經濟部水資源局委託計畫.
[34] Huang.,Huai-En.(2016).濁水溪沖積扇含水層儲蓄回抽場址優選. http://ir.lib.ncu.edu.tw:88/thesis/view_etd.asp?URN=103624007103624007
[35] LaHaye, O. A. (2021). Assessment of Aquifer Storage and Recovery Feasibility in Replenishing Coastal Aquifers and Addressing Flood Mitigation Using Numerical Modeling, Geospatial, and Statistical Techniques: Application in Southwest Louisiana. (Master's thesis). University of Louisiana at Lafayette.
[36] Nienhuis, J. H., Törnqvist, T. E., Jankowski, K. L., Fernandes, A. M., & Keogh, M. E. (2017). A new subsidence map for coastal Louisiana. GSA Today, 27(9), 58-59. https://doi.org/10.1130/GSATG337GW.1
[37] Zheng, C., & Wang, P. P. (1999). MT3DMS: A modular three-dimensional multispecies transport model for simulation of advection, dispersion, and chemical reactions of contaminants in groundwater systems; Documentation and user’s guide. https://hdl.handle.net/11681/4734
[38] Ostad-Ali-Askari, K., Shayannejad, M., & Ghorbanizadeh-Kharazi, H. (2017). Artificial neural network for modeling nitrate pollution of groundwater in marginal area of Zayandeh-rood River, Isfahan, Iran. KSCE Journal of Civil Engineering, 21, 134–140. https://doi.org/10.1007/s12205-016-0572-8
[39] Lin.,Tsai-Chen.(2021).應用因子分析與人工神經網路建立硝酸鹽氮污染潛勢的預測模型. http://ir.lib.ncu.edu.tw:88/thesis/view_etd.asp?URN=108624011108624011
[40] Robert G. Maliva & Thomas M. Missimer(2010)《Aquifer Storage and Recovery and Managed Aquifer Recharge Using Wells: Planning, Hydrogeology, Design, and Operation》