近年，隨著氣候變遷加劇糧食安全問題，政府於2016年國土計畫法通過後開始推動農地永續發展對策、盤點農地資源分類，對農業發展地區進行功能分區劃設。然而，國土計畫「功能分區」係考量農業經營需求、維護生產環境引導農業發展，與內政部國土計畫審議會所制定之「管制分區」，目的係限制土地使用項目而存在管理本質上的差異。鑒於現行國土功能分區過於簡化，缺乏降尺度轉換過程，使得同分類中存在異質性問題，形成土地管理制度上潛在的缺失。

為解決異質性問題，有別於以往採用傳統多變量分析無法處理的研究背景下，本研究首先選定嘉義縣農業發展地區作為實驗範圍，嘗試結合機器學習方法，以最大期望演算法（Expectation-Maximization Algorithm）模擬劃設農地資源，嘗試改善同分類中的異質性問題，並以管理思維納入功能分區，藉以得出「適地適用」的農地管理分區。研究設計上，考量天氣、地力及區位等社經條件方案之貢獻度較高，經分群有效性評估，再細分類嘉義縣農業發展地區，包含「發展優良農地」、「具發展潛力之一般農地」、「敏感型農地」及「不利耕作農地」，並給予不同管理內容。依分類結果，本研究將提出新的農地劃設框架，與現行劃設結果進行差異分析後，供未來農業發展地區劃設參考。

In recent years, with increasing climate change that worsens the situation of food insecurity, the Taiwanese government has promulgated the Spatial Planning Act in 2016 with the strategy of the “Functional Zone” to categorize farmland resources for agricultural sustainability. The primary aim of the Functional Zone is to protect and develop the agricultural land. However, it is not as similar as the “Development Control” from Spatial Planning Committee, which restrict land zones. Since the implementation of Functional Zone in the Act, which in fact is Development Control, oversimplified and lacks of downscaling, the land use management system has the potential mistake that causes the heterogeneity within each land category.

In this paper, we choose Chiayi County as our case and present one method of machine learning, the Expectation-Maximization Algorithm, to improve the problem of heterogeneity, instead of using traditional multivariate analysis. As the condition of weather, soil fertility, and socioeconomics are relatively influential factors to land classification, we evaluated the clustering validity and subdivides the present categories of agricultural areas in Chiayi County into “Advantageous Agricultural Land”, “General Agricultural Land with Potential Development”, “Vulnerable Agricultural Land”, and “Unfavorable Agricultural Land”. This study proposes an innovative agricultural land planning framework, which offers a model for the comparison of present system and future agricultural development.

外文參考文獻
Aguilar-Rivera, N., Algara-Siller, M., Olvera-Vargas, L. A., & Michel-Cuello, C. (2018). Land management in Mexican sugarcane crop fields. Land Use Policy, 78, 763-780.
Ahamed, T. N., Rao, K. G., & Murthy, J. (2000). GIS-based fuzzy membership model for crop-land suitability analysis. Agricultural Systems, 63(2), 75-95.
Ahmed, F., Moors, E., Khan, M. S. A., Warner, J., & Terwisscha Van Scheltinga, C. (2018). Tipping points in adaptation to urban flooding under climate change and urban growth: The case of the Dhaka megacity. Land Use Policy, 79, 496-506. doi:10.1016/j.landusepol.2018.05.051
Ajitesh Kumar (2022). Z-score or Z-statistics: Concepts, Formula & Examples.
Akıncı, H., Özalp, A. Y., & Turgut, B. (2013). Agricultural land-use suitability analysis using GIS and AHP techniques. Computers and electronics in agriculture, 97, 71-82.
Akpoti, K., Kabo-Bah, A. T., Dossou-Yovo, E. R., Groen, T. A., & Zwart, S. J. (2020). Mapping suitability for rice production in inland valley landscapes in Benin and Togo using environmental niche modeling. Science of the total environment, 709, 136165.
Akpoti, K., Kabo-bah, A. T., & Zwart, S. J. (2019). Agricultural land suitability analysis: State-of-the-art and outlooks for integration of climate change analysis. Agricultural systems, 173, 172-208.
Alphan, H. (2003). Land‐use change and urbanization of Adana, Turkey. Land degradation & development, 14(6), 575-586.
Alshari, E. A., & Gawali, B. W. (2021). Development of classification system for LULC using remote sensing and GIS. Global Transitions Proceedings, 2(1), 8-17.
Appiah, J. O., & Agyemang-Duah, W. (2021). Identifying spatially-explicit land-use factors associated with forest patch sizes in a forest reserve in Ghana. Land Use Policy, 101, 105135.
Appiah, J. O., Agyemang-Duah, W., Sobeng, A. K., & Kpienbaareh, D. (2021). Analyzing patterns of forest cover change and related land uses in the Tano-Offin Forest Reserve in Ghana: Implications for forest policy and land management. Trees, Forests and People, 100105.
Appiah, J. O., Opio, C., Venter, O., Donnelly, S., & Sattler, D. (2021). Assessing forest cover change and fragmentation in northeastern British Columbia using Landsat images and a geospatial approach. Earth Systems and Environment, 1-18.
Bailey, T. C., & Gatrell, A. C. (1995). Interactive spatial data analysis (Vol. 413, No. 8). Essex: Longman Scientific & Technical.
Baja, S., Chapman, D. M., & Dragovich, D. (2007). Spatial-based compromise programming for multiple criteria decision-making in land use planning. Environmental Modeling & Assessment, 12(3), 171-184.
Boonyanam, N. (2020). Agricultural economic zones in Thailand. Land Use Policy, 99, 102774.
Borges, J. G., Garcia-Gonzalo, J., Bushenkov, V., McDill, M. E., Marques, S., & Oliveira, M. M. (2014). Addressing multicriteria forest management with Pareto frontier methods: an application in Portugal. Forest Science, 60(1), 63-72.
Bradbury, J. (2014). A keyed classification of natural geodiversity for land management and nature conservation purposes. Proceedings of the Geologists' Association, 125(3), 329-349.
Brahma, B., Nath, A. J., Sileshi, G. W., & Das, A. K. (2018). Estimating biomass stocks and potential loss of biomass carbon through clear-felling of rubber plantations. Biomass and Bioenergy, 115, 88-96.
Braimoh, A., & Vlek, P. (2004). The impact of land‐cover change on soil properties in northern Ghana. Land degradation & development, 15(1), 65-74.
Brown, I., Towers, W., Rivington, M., & Black, H. I. (2008). Influence of climate change on agricultural land-use potential: adapting and updating the land capability system for Scotland. Climate Research, 37(1), 43-57.
Chang, J.-S., Luo, Y.-F., & Su, K.-Y. (1992). GPS: A generalized probabilistic semantic model for ambiguity resolution. Paper presented at the 30th Annual Meeting of the Association for Computational Linguistics.
Chi, G., Gao, J., Wang, D., Hagedorn, A., Kelgenbaeva, K., Smith, M. L., & Henebry, G. M. (2020). Agricultural production at the oblast level in post-Soviet Kyrgyzstan, 1990–2014: Implications of demographic and climate changes. Research in Globalization, 2. doi:10.1016/j.resglo.2020.100027
Devine, S. M., Steenwerth, K. L., & O'Geen, A. T. (2021). A areaal soil classification framework to improve soil health diagnosis and management. Soil Science Society of America Journal, 85(2), 361-378. doi:10.1002/saj2.20200
De Carlo, T. E., Romano, A., Waheed, N. K., & Duker, J. S. (2015). A review of optical coherence tomography angiography (OCTA). International journal of retina and vitreous, 1(1), 1-15.
Dong, J., Xiao, X., Kou, W., Qin, Y., Zhang, G., Li, L., . . . Biradar, C. (2015). Tracking the dynamics of paddy rice planting area in 1986–2010 through time series Landsat images and phenology-based algorithms. Remote Sensing of Environment, 160, 99-113.
Fakoya, E., Agbonlahor, M., & Dipeolu, A. (2007). The attitude of women farmers towards sustainable land management practices in South-Western Nigeria. World journal of agricultural sciences, 3(4), 536-542.
Feizizadeh, B., & Blaschke, T. (2012). Uncertainty analysis of GIS-based ordered weighted averaging method for landslide susceptibility mapping in Urmia Lake Basin, Iran. Paper presented at the Seventh International Geographic Information Science Conference, September.
Filippi, P., Jones, E. J., Wimalathunge, N. S., Somarathna, P. D., Pozza, L. E., Ugbaje, S. U., . . . Bishop, T. F. (2019). An approachforecastingcast grain crop yield using multi-layered, multi-farm data sets and machine learning. Precision Agriculture, 20(5), 1015-1029.
Frias-Martinez, V., & Frias-Martinez, E. (2014). Spectral clustering for sensing urban land use using Twitter activity. Engineering Applications of Artificial Intelligence, 35, 237-245.
Gao, L., Zhang, W., Mei, Y., Sam, A. G., Song, Y., & Jin, S. (2018). Do farmers adopt fewer conservation practices on rented land? Evidence from straw retention in China. Land Use Policy, 79, 609-621. doi:10.1016/j.landusepol.2018.08.026
Gavioli, A., de Souza, E. G., Bazzi, C. L., Schenatto, K., & Betzek, N. M. (2019). Identification of management zones in precision agriculture: An evaluation of alternative cluster analysis methods. BiosysteEngineeringing, 181, 86-102.
Gay, C., Estrada, F., Conde, C., Eakin, H., & Villers, L. (2006). Potential impacts of climate change on agriculture: a case of study of coffee production in Veracruz, Mexico. Climatic Change, 79(3), 259-288.
Geisser, S. (1974). A predictive approach to the random effect model. Biometrika, 61(1), 101-107.
Geisser, S., & Eddy, W. F. (1979). A predictive approach to model selection. Journal of the American Statistical Association, 74(365), 153-160.
Gopalakrishnan, G., Cristina Negri, M., & Snyder, S. W. (2011). A novel framework to classify marginal land for sustainable biomass feedstock production. Journal of environmental quality, 40(5), 1593-1600.
Hopkins, L. D. (1977). Methods for generating land suitability maps: a comparative evaluation. Journal of the American Institute of Planners, 43(4), 386-400.
Huang, K., Leng, J., Xu, Y., Li, X., Cai, M., Wang, R., & Ren, C. (2021). Facilitating urban climate forecasts in rapidly urbanizing areas with land-use change modeling. Urban Climate, 36, 100806.
International Panel on Climate Change (2019). Climate change and land, an IPCC special report on climate change, desertification, land degradation, sustainable land management, food security, and greenhouse gas fluxes in terrestrial ecosystems. Geneva, Switzerland: IPCC.
Jafari, S., & Zaredar, N.(2010). Land Suitability Analysis using Multi AttributeDecision Making Approach. International journal of environmental science and development, 1(5), 441.
Jurišić, M., Radočaj, D., Krčmar, S., Plaščak, I., & Gašparović, M. (2020). Geostatistical analysis of soil C/N deficiency and its effect on agricultural land management of major crops in eastern Croatia. Agronomy, 10(12), 1996.
Kanakis, M. E., Khalili, R., & Wang, L. (2022). Machine Learning for Computer Systems and Networking: A Survey. ACM Computing Surveys (CSUR).
Kostrowicki, J. (1964). Geographical Typology of Agriculture, Principles, and Methods. An invitation to discussion. Revista Geográfica, 15-24.
Könnyű, N., Tóth, S. F., McDill, M. E., & Rajasekaran, B. (2014). Temporal connectivity of mature patches in forest planning models. Forest Science, 60(6), 1089-1099.
Kohavi, R. (1995). A study of cross-validation and bootstrap for accuracy estimation and model selection. Paper presented at the Ijcai.
Korzhiniskii, D. (1970). Theory of Metasomatie Zoning: Oxford University Press.
Khan, M. S. A., Mehdi, S. M., Sheikh, A. A., Khan, A. G., Shakar, M., Alvi, A., . . . David, M. (2018). Delineation of nutrient management zones in churning using soil attributes database developed by soil fertility research institute, Punjab, Pakistan. Soil Environ, 37, 116-122.
Lengyel, A., & Botta‐Dukát, Z. (2019). Silhouette width using generalized mean—A flexible method for assessing clustering efficiency. Ecology and Evolution, 9(23), 13231-13243.
Li, Y., Westlund, H., & Liu, Y. (2015). Urban-rural transformation about cultivated land conversion in China: Implications for optimizing land use and balanced areaal development. Land Use Policy, 47, 218-224.
Malczewski, J. (2006). Ordered weighted averaging with fuzzy quantifiers: GIS-based multicriteria evaluation for land-use suitability analysis. International journal of applied earth observation and geoinformation, 8(4), 270-277.
Marques, M. J., Bienes, R., Cuadrado, J., Ruiz‐Colmenero, M., Barbero‐Sierra, C., & Velasco, A. (2015). Analyzing perceptions attitudes and responses of winegrowers about sustainable land management in Central Spain. Land degradation & development, 26(5), 458-467.
Mather, A. S. (2002). The reversal of land-use trends: the beginning of the reforestation of Europe. In: Land use/land cover changes in the period of globalization (eds. Bicik, I.; Chromy, P.; Janiak, V.; Janu, H.) Charles University and IGU-LUCC (pp. 23-30).
McDill, M. E. (2014). An overview of forest management planning and information management. The management of industrial forest plantations, 27-59.
McHarg, I. L. (1969). Design with nature: American Museum of Natural History New York.
MINISTRY OF AGRICULTURE. (1988). Agricultural Land Classification of England and Wales: Revised Guidelines and Criteria for Grading the Quality of Agricultural Land. Ministry.
Nath, A. J., Kumar, R., Devi, N. B., Rocky, P., Giri, K., Sahoo, U. K., . . . Pandey, R. (2021). Agroforestry land suitability analysis in the Eastern Indian Himalayan area. Environmental Challenges, 4, 100199.
Niroula, G. S., & Thapa, G. B. (2005). Impacts and causes of land fragmentation, and lessons learned from land consolidation in South Asia. Land Use Policy, 22(4), 358-372.
OECD, I. (2016). Energy and air pollution: world energy outlook special report 2016.
Paül, V., & McKenzie, F. H. (2013). Peri-urban farmland conservation and development of alternative food networks: Insights from a case-study area in metropolitan Barcelona (Catalonia, Spain). Land use policy, 30(1), 94-105.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., . . . Dubourg, V. (2011). Scikit-learn: Machine learning in Python. the Journal of Machine Learning Research, 12, 2825-2830.
Pokharel, B., Althuwaynee, O. F., Aydda, A., Kim, S.-W., Lim, S., & Park, H.-J. (2021). Spatial clustering and modeling for landslide susceptibility mapping in the north of the Kathmandu Valley, Nepal. Landslides, 18(4), 1403-1419.
Porter, J. R., Xie, L., Challinor, A. J., Cochrane, K., Howden, S. M., Iqbal, M. M., . . . Travasso, M. I. (2014). Food security and food production systems.
Posthumus, H., Morris, J., Hess, T. M., Neville, D., Phillips, E., & Baylis, A. (2009). Impacts of the summer 2007 floods on agriculture in England. Journal of Flood Risk Management, 2(3), 182-189. doi:10.1111/j.1753-318x.2009.01031.x
Prijith, S. S., Srinivasarao, K., Lima, C. B., Gharai, B., Rao, P. V. N., Seshasai, M. V. R., & Ramana, M. V. (2021). Effects of land use/land cover alterations on areaal meteorology over Northwest India. Science of the total environment, 765, 142678. doi:10.1016/j.scitotenv.2020.142678
Radočaj, D., Jurišić, M., & Antonić, O. (2021). Determination of soil C: N suitability zones for organic farming using an unsupervised classification in eastern Croatia. Ecological Indicators, 123, 107382.
Rajapaksa, D., Islam, M., & Managi, S. (2018). Pro-Environmental Behavior: The Role of Public Perception in Infrastructure and the Social Factors for Sustainable Development. Sustainability, 10(4), 937. doi:10.3390/su10040937
Rega, C., Short, C., Pérez-Soba, M., & Paracchini, M. L. (2020). A classification of European agricultural land using an energy-based intensity indicator and detailed crop description. Landscape and Urban Planning, 198, 103793.
Renwick, A., Jansson, T., Verburg, P. H., Revoredo-Giha, C., Britz, W., Gocht, A., & McCracken, D. (2013). Policy reform and agricultural land abandonment in the EU. Land use policy, 30(1), 446-457.
Richard, A. J. (2007). Applied multivariate statistical analysis.
Romano, G., Dal Sasso, P., Liuzzi, G. T., & Gentile, F. (2015). Multi-criteria decision analysis for land suitability mapping in a rural area of Southern Italy. Land Use Policy, 48, 131-143.
Roose, A., Kull, A., Gauk, M., & Tali, T. (2013). Land use policy shocks in the post-communist urban fringe: A case study of Estonia. Land Use Policy, 30(1), 76-83.
Rousseeuw, P. J. (1987). Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. Journal of computational and applied mathematics, 20, 53-65.
Semple, E. C. (1912). Influence of Geographical Conditions upon Japanese Agriculture. The Geographical Journal, 40(6), 589-603.
Senthilnath, J., Omkar, S., Mani, V., Tejovanth, N., Diwakar, P., & Shenoy, A. B. (2012). Hierarchical clustering algorithm for land cover mapping using satellite images. IEEE Journal of selected topics in applied earth observations and remote sensing, 5(3), 762-768.
Su, M., Guo, R., Chen, B., Hong, W., Wang, J., Feng, Y., & Xu, B. (2020). Sampling strategy for detailed urban land use classification: A systematic analysis in Shenzhen. Remote Sensing, 12(9), 1497.
Thoumazeau, A., Bessou, C., Renevier, M.-S., Trap, J., Marichal, R., Mareschal, L., . . . Chevallier, T. (2019). Biofunctool®: a new framework to assess the impact of land management on soil quality. Part A: concept and validation of the set of indicators. Ecological Indicators, 97, 100-110.
Thoumazeau, A., Chevallier, T., Baron, V., Rakotondrazafy, N., Panklang, P., Marichal, R., . . . Bessou, C. (2020). A new in-field indicator to assess the impact of land management on soil carbon dynamics. Geoderma, 375, 114496.
Ugbaje, S. U., Odeh, I. O., & Bishop, T. F. (2019). Fuzzy measure-based multicriteria land assessment for rainfed maize in West Africa for the current and a range of plausible future climates. Computers and electronics in agriculture, 158, 51-67.
Useya, J., & Chen, S. (2019). Exploring the potential of mapping cropping patterns on smallholder scale croplands using sentinel-1 SAR data. Chinese Geographical Science, 29(4), 626-639.
Wu, Z., Thenkabail, P. S., Mueller, R., Zakzeski, A., Melton, F., Johnson, L., . . . Verdin, J. P. (2014). Seasonal cultivated and fallow cropland mapping using MODIS-based automated cropland classification algorithm. Journal of Applied Remote Sensing, 8(1), 083685.
Yalew, S. G., Van Griensven, A., Mul, M. L., & van der Zaag, P. (2016). Land suitability analysis for agriculture in the Abbay basin using remote sensing, GIS, and AHP techniques. Modeling Earth Systems and Environment, 2(2), 1-14.
Yang, J., Sun, P., Zhang, X., Wei, X.-Y., Huang, Y.-P., Du, W.-N., . . . Huang, Y. (2021). Source apportionment of PAHs in roadside agricultural soils of a megacity using positive matrix factorization receptor model and compound-specific carbon isotope analysis. Journal of Hazardous Materials, 403, 123592. doi:10.1016/j.jhazmat.2020.123592
Yang, X., Zheng, X.-Q., & Chen, R. (2014). A land-use change model: Integrating landscape pattern indexes and Markov-CA. Ecological Modelling, 283, 1-7.
Yousefpour, R., Jacobsen, J. B., Thorsen, B. J., Meilby, H., Hanewinkel, M., & Oehler, K. (2012). A review of decision-making approaches to handle uncertainty and risk in adaptive forest management under climate change. Annals of forest science, 69(1), 1-15.
Zhao, Y., Gong, P., Yu, L., Hu, L., Li, X., Li, C., . . . Zhao, Y. (2014). Towards a common validation sample set for global land-cover mapping. International Journal of Remote Sensing, 35(13), 4795-4814.

中文參考文獻
王素芬（2001）。森林生態系經營決策支援系統：以六龜試驗林為例（博士論文）。國立臺灣大學森林學研究所。
吳振發（2004）。農地轉用方案之地景生態效益評估。經社法制論叢，33期。
林裕彬、林信輝、陳秋楊（2003）。應用遙測影像及景觀生態計量方法於集水區土地利用變遷之研究（碩士論文）。中國文化大學地學研究所。
林漢彬（2014）。國土計畫法下城鄉發展區劃設之研究-以台中地區為例（碩士論文）。國立成功大學都市計劃學系。
馬世發、黃宏源、蔡玉梅、念沛豪（2014）。基於三生功能優化的國土空間綜合分區理論框架。中國國土資源經濟，27(11)，31-34。
張秀珍、鄒克萬、張曜麟（2000）。都市地價之空間態變化特性研究，地理學與區域發展學術討會論文集。國立彰化師範大學地理學系。
張益三（1999）。以土地適宜性特性及汙染涵容能力觀點探討山坡地水源保護區土地使用計畫模式。國科會專題研究（NSC88-2415-H-006-013）。
張學聖、陳姿伶、陳柏君（2013）。台灣農地轉用與農地交易空間關聯性之研究。建築學報，14(2/3)，167-182。
陳彥勳、李盈潔（2020）。農地景觀特徵之生態系統服務功能初探。農林學報，67(4)，233-248。
陳維斌、李俊霖、張琪如、王瓊芯（2016）。蘭陽平原農地轉用影響因子分析與空間規劃政策探討：系統方法之引入。台灣土地研究，19(2)，1-35。
黃志成、汪家夷（2002）。森林遊樂區發展生態旅遊之土地使用分區研究—以惠蓀林場為例。（碩士論文）。朝陽科技大學休閒事業管理系。
黃書禮（2000）。生態土地使用規劃，初版，台北市，詹氏書局。
葉佳宗（2021）。永續農業土地利用與管理—趨勢、挑戰與政策建議。農業觀點，
（343-354），69-79。
詹家佳（2006）。淡海新市鎮的發展（碩士論文）。臺灣師範大學地理學系在職進修碩士班學位論文，1-101。
行政院農業委員會（1994）。折衷農耕法具發展潛力。高雄區農業專訊，1-32。
行政院農業委員會（2009）。嘉義縣中埔鄉農地資源空間規劃計畫案。
行政院農業委員會（2011）。農委會年報。
行政院農業委員會（2018），107年度農地資源空間規劃總顧問指導計畫。
行政院農業委員會（2019），108年度農地資源空間規劃總顧問指導計畫。
嘉義縣政府（2018）。嘉義縣配合國土計畫推動農地資源空間規劃計畫。
嘉義縣政府（2019）。嘉義縣配合國土計畫推動農地資源空間規劃計畫。
營建署（2021）。國土功能分區及分類與使用地劃設作業手冊。
羅凱揚、蘇宇暉、鍾皓軒（2019）。行銷資料科學。新北市：碁峰資訊有限公司。

網路參考資料
Chire (2010). k-means clustering. https://en.wikipedia.org/wiki/K-means_clustering
Jason (2019). Cross-Validation. https://jason-chen-1992.weebly.com/home/-cross-alidation
林秉勳（2017年12月19日）。營建署：國土計畫法預計111年5月上路。雅虎奇摩 新聞。https://tw.sports.yahoo.com/news -121636347.html