[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125318-en":3,"doc-seo-125318-105":31,"detail-sidebar-cat-0-en-105":93},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":28,"update_tm":29,"read_time":30},125318,962075114765,"Quinn","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Machine Learning for Semi-Automated Land Parcel Plotting","\u003Cp>Indonesia’s cadastral quality improvement program launched in 2018 faces major difficulties caused by the country’s vast territory, heterogeneous natural and social conditions, and legacy mapping practices. With about 15 million land parcels still unplotted accurately, a machine-learning solution is proposed to accelerate plotting from old land certificates and cadastral maps. The method uses a heuristic-driven geospatial matching procedure informed by manual practices, and optimizes a geometric-attribute model using RCGA, achieving strong recall and precision on test and real data.\u003C/p>","\u003Cp>Machine Learning for Semi-Automated Land Parcel Plotting  \u003C/p>\u003Cp>Muhammad Ghaly Kurniawan 1,2 , Malumbo Chipofya 1 (B) , and Dimo Todorovski 1  \u003C/p>\u003Cp>1 Faculty ITC, University of Twente, Hallenweg 8, 7522 NH Enschede, The Netherlands [m.c.chipofya@utwente.nl](m.c.chipofya@utwente.nl)  \u003C/p>\u003Cp>2 Ministry of Agrarian Affairs and Spatial Planning/National Land Agency, Jakarta, Indonesia  \u003C/p>\u003Cp>Abstract. The Indonesian cadastral quality improvement process, established in 2018, faces huge challenges due to its huge land area, diverse natural and social conditions, and historical mapping practices. With15million land parcels yet tobe plotted accurately, in this work we propose a solution based on machine learning to speed up the process of plotting parcels documented on old land certificatesand maps. Our approach is a heuristic-driven geospatial data matching procedure that semi-automatically searches for possible locations for plotting land parcels.  \u003C/p>\u003Cp>The heuristic aspect of the approach is its basis in the manual plotting method in use presently in Indonesia. We identified eight causes of unplotted parcels and for two of these causes we have implemented an optimization algorithm model defined over five geometric parcel attributes. The model is then optimized using the RCGA algorithm. The model performed with recall rates of 88.3% and 57% on test data and real data respectively, and precision rates of 98.8% and 91% also respectively for test data and real data. After the incorporation of text information in old cadastral maps, the recall value for real data improved to 91% .  \u003C/p>\u003Cp>Keywords: Land administration · Cadastral quality improvement · Unplotted land parcels · RCGA optimization algorithm · Machine learning · Spatial data matching  \u003C/p>\u003Cp>1 Introduction  \u003C/p>\u003Cp>Indonesia is one of the countries that is working on cadastral quality improvements. Cadastral quality improvement in Indonesia started in 2018 in the city of Surakarta and continues to other major cities such as Jakarta, Batam, Pontianak, Bali, and Surabaya. The large landarea, the diversity ofits nature and social structure, and historical mapping practices and legal precedents bring challenges in the replotting process of old cadastral maps in Indonesia. There are approximately 126 million land parcels in Indonesia, and 100 million of them are already mapped in the GIS database. From that number, there are approximately 21 million parcels that are not yet plotted in the correct location [1] . To plot that huge number of parcels, using a manual searching method is not feasible in the short-to near-term. Meanwhile, delaying the time of plotting creates the potential for land conflicts. Such conflicts can escalate into violent conflict if not well managed and anticipated [2] .  \u003C/p>\u003Cp>© The Author(s), under exclusive license to Springer Nature Switzerland AG 2025  \u003C/p>\u003Cp>A. Abdul-Rahman et al. (Eds.): GeoWeek 2024, LNGC, pp. 95–111, 2025.  \u003C/p>\u003Cp>[https://doi.org/10.1007/978-3-031-86654-8](https://doi.org/10.1007/978-3-031-86654-8_8)[_](https://doi.org/10.1007/978-3-031-86654-8_8)[8](https://doi.org/10.1007/978-3-031-86654-8_8)  \u003C/p>\u003Cp>In this work, we propose a solution based on machine learning to speed up the process of plotting parcels documented on old land certificates and cadastral maps. The challenges of this task can be categorized into technical challenges and legal ones. The legal challenges appear as a result of previous regulations that allowed land certificates tobe issued without the maps on them. Government Regulation 10/1961 of the Republic of Indonesia [3] stated that if the measurement letter (Surat Ukur) cannot be produced for some reason, a replacement certificate can be issued that has the same function as the certificate. It means that those types ofcertificateshave the same legal force asthe normal ones and also need to be plotted in the current cadastral database. The big question then arises of how to plot parcels for which the corresponding land certificates have no maps or spatial data attached to them.  \u003C/p>\u003Cp>The tech\u003C/p>","cbCaioVJrYCU1pda","https://ap.wps.com/l/cbCaioVJrYCU1pda","pdf",3594718,1,17,"English","en",105,"# Abstract\n# Introduction\n## Background and challenges in Indonesia\n# Literature Review\n## Cadastral quality improvement process","[{\"question\":\"What problem does the paper address in Indonesia’s cadastral improvement program?\",\"answer\":\"It targets the challenge of accurately plotting large numbers of land parcels documented on old land certificates and cadastral maps, where many parcels remain unplotted due to legacy mapping and missing or unclear spatial information.\"},{\"question\":\"How does the proposed approach semi-automatically find candidate parcel locations?\",\"answer\":\"It applies a heuristic-driven geospatial data matching procedure based on the manual plotting method currently used in Indonesia, then semi-automatically searches possible locations for plotting.\"},{\"question\":\"What optimization method is used and what results are reported?\",\"answer\":\"The geometric-attribute model is optimized using the RCGA algorithm. Reported recall and precision rates are high on test data, and recall improves after incorporating text information from old cadastral maps on real data.\"}]","Machine Learning for Semi-Automated Land Parcel Plotting  | PDF","Indonesia’s cadastral quality improvement program launched in 2018 faces major difficulties caused by the country’s vast territory, heterogeneous natural and social conditions, and legacy mapping practices. With about 15 million land parcels still unplotted accurately, a machine-learning solution is proposed to accelerate plotting from old land certificates and cadastral maps. The method uses a heuristic-driven geospatial matching procedure informed by manual practices, and optimizes a geometric-attribute model using RCGA, achieving strong recall and precision on test and real data.",1785899149,43,{"code":4,"msg":32,"data":33},"ok",{"site_id":24,"language":23,"slug":34,"title":35,"keywords":36,"description":28,"schema_data":37,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"machine-learning-for-semi-automated-land-parcel-plotting-rcga-optimization-and-heuristic-spatial-data-matching","Machine Learning for Semi-Automated Land Parcel Plotting ","",{"@graph":38,"@context":87},[39,56,70],{"@type":40,"itemListElement":41},"BreadcrumbList",[42,46,50,53],{"item":43,"name":44,"@type":45,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":47,"name":48,"@type":45,"position":49},"https://docshare.wps.com/document/","Document",2,{"item":51,"name":12,"@type":45,"position":52},"https://docshare.wps.com/document/research-report/",3,{"item":54,"name":13,"@type":45,"position":55},"https://docshare.wps.com/document/machine-learning-for-semi-automated-land-parcel-plotting-rcga-optimization-and-heuristic-spatial-data-matching/125318/",4,{"url":54,"name":35,"@type":57,"author":58,"headline":35,"publisher":60,"fileFormat":63,"inLanguage":23,"description":28,"dateModified":64,"datePublished":64,"encodingFormat":63,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":59},"Person",{"url":43,"name":61,"@type":62},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":4},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"What problem does the paper address in Indonesia’s cadastral improvement program?","Question",{"text":77,"@type":78},"It targets the challenge of accurately plotting large numbers of land parcels documented on old land certificates and cadastral maps, where many parcels remain unplotted due to legacy mapping and missing or unclear spatial information.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"How does the proposed approach semi-automatically find candidate parcel locations?",{"text":82,"@type":78},"It applies a heuristic-driven geospatial data matching procedure based on the manual plotting method currently used in Indonesia, then semi-automatically searches possible locations for plotting.",{"name":84,"@type":75,"acceptedAnswer":85},"What optimization method is used and what results are reported?",{"text":86,"@type":78},"The geometric-attribute model is optimized using the RCGA algorithm. Reported recall and precision rates are high on test data, and recall improves after incorporating text information from old cadastral maps on real data.","https://schema.org",{"og:url":54,"og:type":89,"og:title":35,"og:site_name":61,"og:description":28},"article",{"robots":91,"canonical":54},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":94},[95,99,103,107,112,117,122,125,130,133,137],{"id":20,"doc_module":4,"doc_module_name":48,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":49,"doc_module":4,"doc_module_name":48,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":55,"doc_module":4,"doc_module_name":48,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":108,"doc_module":4,"doc_module_name":48,"category_name":109,"show_sort_weight":110,"slug":111},5,"Comic",60,"comic",{"id":113,"doc_module":4,"doc_module_name":48,"category_name":114,"show_sort_weight":115,"slug":116},6,"Technology",50,"technology",{"id":118,"doc_module":4,"doc_module_name":48,"category_name":119,"show_sort_weight":120,"slug":121},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":48,"category_name":12,"show_sort_weight":123,"slug":124},30,"research-report",{"id":126,"doc_module":4,"doc_module_name":48,"category_name":127,"show_sort_weight":128,"slug":129},9,"Religion & Spirituality",20,"religion-spirituality",{"id":128,"doc_module":4,"doc_module_name":48,"category_name":131,"show_sort_weight":128,"slug":132},"World Cup","world-cup",{"id":134,"doc_module":4,"doc_module_name":48,"category_name":135,"show_sort_weight":134,"slug":136},10,"Lifestyle","lifestyle",{"id":138,"doc_module":4,"doc_module_name":48,"category_name":139,"show_sort_weight":108,"slug":140},19,"General","general"]