AI, Parcel Mapping and Land Surveying - Will Artificial Intelligence Replace Parcel Mappers and Land Surveyors?

Artificial intelligence has become the topic of nearly every professional conversation. It is writing software that generates artwork, answers technical questions, produces legal documents, and increasingly performs tasks once believed to require significant human expertise. It is only natural that professionals responsible for maintaining cadastral records and establishing land boundaries begin asking an important question:

Will artificial intelligence eventually replace parcel mappers and land surveyors?

The short answer is no—or at least not in the foreseeable future.

While AI will undoubtedly transform many aspects of our profession, the fundamental nature of boundary determination and parcel mapping depends upon something that artificial intelligence cannot easily replicate: the interpretation of imperfect evidence in the physical world.

The Difference Between Information and Evidence

Artificial intelligence excels when working with information that exists in digital form. It can analyze millions of documents, summarize legal opinions, extract text from deeds, identify patterns in parcel histories, and even assist in drafting legal descriptions.

Unfortunately, property boundaries are rarely determined solely from written information.

A deed may describe a property as running “to an old oak tree,” “along the centerline of the creek,” or “to the iron pipe set by John Smith in 1948.” The document itself provides only part of the story. The remainder exists on the ground, where physical evidence has weathered decades of change.

The true location of a boundary often depends upon evaluating monuments, occupation lines, fences, hedgerows, stone walls, roads, witness testimony, historical surveys, adjoining conveyances, and the actions of neighboring landowners. These are not merely pieces of information—they are pieces of evidence.

Evidence must be discovered, evaluated, weighed, and reconciled.

That process remains fundamentally human.

Boundary Resolution Is Not a Mathematical Exercise

Many people unfamiliar with surveying assume that determining a property boundary is simply a matter of mathematics.

If only it were that simple.

Modern software can compute coordinate geometry with extraordinary precision. AI can solve complex geometric problems almost instantly. Yet the greatest challenge in boundary retracement is rarely computing where a line should be.

The challenge is determining where the line was intended to be.

Legal intent often overrides mathematical precision. Original monuments frequently control over calculated positions. Senior rights may supersede later conveyances. Long-standing occupation may influence boundary location. Missing monuments require interpretation rather than calculation.

Artificial intelligence can perform the mathematics.

It cannot independently determine which evidence carries the greatest legal weight.

Every Parcel Is a Historical Investigation

One of the defining characteristics of cadastral work is that every parcel carries its own history.

A parcel created in 2025 may be relatively straightforward. However, we must also realize that all parcels are created from older, original parcels and the land interests established prior to their creation.

A parcel created in 1825 may involve:

  • Multiple deed transfers

  • Conflicting surveys

  • Road relocations

  • River movements

  • Lost monuments

  • Fence relocations

  • Easements

  • Adverse possession claims

  • Judicial decisions

  • Vacations and dedications

  • Boundary agreements

No two situations are identical.

Each requires professional judgment developed through years of experience studying boundary law, surveying principles, historical records, and local practices.

AI can certainly organize this information.

Determining what it all means is another matter entirely.

The Physical World Cannot Be Fully Digitized

Parcel mapping ultimately attempts to model a physical world that is far more complex than any database.

Even the most sophisticated GIS represents only our best and most recent interpretation of reality.

Artificial intelligence cannot walk through dense vegetation searching for a buried iron rod.

It cannot determine whether a fence has stood undisturbed for seventy years.

It cannot interview adjoining landowners about long-recognized occupation.

It cannot recognize subtle evidence visible only to someone standing on the property.

Nor can it replace the professional responsibility that comes with signing a survey.

Boundary surveying remains one of the few professions in which digital information must continually be reconciled with physical evidence.

Parcel Mapping Requires Judgment

Parcel mappers face similar challenges.

Contrary to popular belief, parcel mapping is not simply tracing deeds into GIS.

Every parcel map represents countless decisions involving:

  • Which document controls

  • How conflicting descriptions should be reconciled

  • Whether subdivisions supersede previous conveyances

  • How easements interact with ownership

  • Whether tax parcels differ from legal parcels

  • How to maintain historical parcel lineage

  • When geometry should reflect legal intent rather than measured coordinates

These decisions often require knowledge of local statutes, recording practices, historical mapping methods, and surveying principles.

Artificial intelligence may recommend possible interpretations.

The mapper remains responsible for selecting the correct one.

Where AI Will Make a Tremendous Difference

Although AI is unlikely to replace parcel professionals, it will almost certainly become an indispensable assistant.

Imagine AI capable of:

  • Reading thousands of deeds and extracting legal descriptions.

  • Identifying possible parent-child parcel relationships.

  • Suggesting subdivision lineage.

  • Comparing multiple legal descriptions for inconsistencies.

  • Detecting probable drafting errors.

  • Flagging parcels with conflicting acreage.

  • Summarizing title histories.

  • Identifying likely monument references.

  • Recommending adjoining documents for review.

  • Assisting in drafting parcel fabric edits.

  • Generating preliminary legal descriptions.

  • Automatically classifying recorded documents.

  • Searching historical map collections in seconds.

These are tasks that consume enormous amounts of professional time today.

Rather than replacing experts, AI will allow them to focus on the work requiring human judgment.

Professional Judgment Cannot Be Automated

The defining characteristic of both land surveyors and parcel mappers is not their ability to calculate geometry.

Software has performed calculations for decades.

The defining characteristic is professional judgment.

Professional judgment is built upon experience, education, ethics, and accountability.

It requires understanding not only what the evidence says, but why it exists and how courts have historically interpreted similar situations.

Artificial intelligence does not bear legal responsibility.

It cannot testify in court.

It cannot sign a survey.

It cannot assume liability for an incorrect boundary determination.

Ultimately, someone must make the final decision.

That responsibility belongs to licensed professionals and experienced parcel managers.

The Future Is Collaboration, Not Replacement

History suggests that technology rarely eliminates professions built upon expert judgment.

Instead, it changes the nature of the work.

Calculators did not replace engineers.

Computer-aided drafting did not replace architects.

GIS did not replace surveyors.

Likewise, artificial intelligence will not eliminate parcel mapping or land surveying.

Instead, it will automate repetitive tasks, accelerate research, reduce clerical effort, and help professionals analyze far more information than ever before.

The profession will evolve from spending countless hours searching for information toward spending more time interpreting it.

The Human Element Remains Essential

Land ownership is one of society’s oldest and most important legal institutions. Property boundaries define ownership, taxation, development, public infrastructure, environmental stewardship, and individual rights. Because of the legal and societal significance of those boundaries, determining their location has never been a purely technical exercise.

Artificial intelligence will undoubtedly become one of the most powerful tools ever introduced into the surveying and parcel mapping professions. It will improve efficiency, reduce repetitive work, and reveal insights hidden within vast collections of deeds, plats, and historical records. But the final determination of a boundary will continue to depend on professional judgment, legal interpretation, and the careful evaluation of physical evidence.

The future of parcel mapping is therefore not one where artificial intelligence replaces surveyors and parcel mappers. It is one in which experienced professionals leverage AI to become even more capable, allowing technology to handle routine tasks while humans remain responsible for the decisions that ultimately define the limits of land ownership.

The Hidden Cost of Going It Alone: Why GIS Needs Data Governance Across Departments

Geographic Information Systems (GIS) have become the backbone of modern organizations — helping departments map infrastructure, manage assets, and make data-driven decisions. But too often, the power of GIS is limited not by technology, but by people and process. One of the most common and costly challenges organizations face is operating GIS without a data governance agreement that defines authoritative layers, schemas, standards of service, and responsibilities between departments.

Without clear governance, even the best GIS platform can become a patchwork of disconnected datasets, conflicting priorities, and uncertain accountability.

The Challenge of “Multiple Versions of the Truth”

When every department maintains its own GIS layers without coordination, it’s only a matter of time before inconsistencies emerge.

The Planning Department’s parcel layer may not align with the one used by Public Works for utility management.

Emergency Services may update address points independently, unaware that another group is managing the same data for 911 response.

Departments might even disagree on what dataset is authoritative — meaning which one should be trusted as the official source.

The result? Confusion, duplication, and mistrust. Decision-makers begin to question the validity of the data itself. Projects slow down as staff scramble to reconcile discrepancies or verify information that should have been standardized from the outset.

Schema Drift and Compatibility Issues

Without agreed-upon schemas (the data structure or model that defines how features are named, coded, and related), GIS databases can quickly diverge from one another.

One team might name a field “Parcel_ID,” while another uses “ParcelNumber.”

One layer might store acreage as a floating-point number, while another stores it as text.

These minor differences add up to big integration headaches. Automated scripts fail. Analytical models break. And what should be a seamless exchange of information across systems becomes a manual, error-prone process.

Governance doesn’t just mean having the same data — it means having data that works together.

Lack of Service Standards and Performance Expectations

When there’s no governance agreement, each department may have its own understanding of service levels:

How frequently should data be updated

Who is responsible for QA/QC

How requests for new data or edits should be prioritized

What response times users should expect from GIS support teams

The absence of standards of service creates friction and unmet expectations. Departments relying on GIS for time-sensitive operations, such as permitting, emergency management, or field inspections, can find themselves working with outdated or incomplete data.

A governance agreement clarifies these expectations, ensuring that the organization’s GIS infrastructure supports everyone effectively and consistently.

Unclear Roles and Responsibilities

Another common pain point is the question of “Who owns what?”

When data ownership and stewardship aren’t clearly assigned, essential maintenance tasks often fall through the cracks. Metadata goes out of date. Edits are made inconsistently. Layers get replaced, duplicated, or deleted without notice.

Without defined roles, accountability disappears — and so does trust in the system.

A governance framework explicitly defines:

Who owns each dataset

Who maintains it

Who has the authority to edit, approve, or publish it

How conflicts or errors are resolved

This clarity helps prevent both accidental errors and interdepartmental friction.

Strategic Impacts: Slowed Innovation and Missed Opportunities

When departments work in isolation, the entire organization loses out on the collective value of GIS.

Without shared standards or collaboration, it isn’t easy to:

Build enterprise dashboards that integrate data from multiple sources

Develop web maps and applications that rely on standardized schemas

Support AI and analytics workflows that require consistent and reliable data inputs

In other words, a lack of governance turns GIS from a strategic asset into a siloed tool. The organization spends more time managing data than using it to solve problems.

The Path Forward: Building a Data Governance Agreement

Establishing GIS data governance doesn’t have to be bureaucratic or heavy-handed. It simply requires a clear, shared understanding of how data should be managed and maintained. A strong governance agreement typically includes:

Authoritative Layers: Which datasets are considered the official source for each topic (parcels, roads, addresses, etc.).

Data Schemas: Field names, data types, and coding conventions that ensure compatibility across systems.

Standards of Service: Expectations for update frequency, quality control, and user support.

Roles and Responsibilities: Clear assignments for data stewards, editors, publishers, and reviewers.

Change Management Process: How new layers, schema changes, or data corrections are proposed and approved.

When organizations formalize these elements, collaboration becomes easier, data becomes more reliable, and GIS can finally deliver on its promise of providing a single, trusted source of truth.

In Closing

GIS is at its most potent when it connects, not divides, departments. But achieving that connection requires more than technology; it requires governance.

Without a data governance agreement, an organization risks wasting effort, achieving inconsistent results, and missing opportunities. With one, it gains confidence, clarity, and a foundation for more intelligent decisions.

In the end, GIS isn’t just about maps — it’s about management. And data governance is the roadmap that keeps everyone moving in the same direction.

Embracing Productive Failure in GIS: Why Mistakes Drive Better Mapping

If you’ve ever built a geodatabase, wrestled with coordinate systems, or tried to reconcile parcel boundaries that simply won’t close, you already know this truth: working in GIS is a cycle of trial, error, correction, and improvement. Yet many GIS professionals hesitate to embrace the value of failure. We often strive for flawless workflows and clean outputs, but overlooking the role of mistakes can hinder our ability to learn from deeper insights and drive innovation.

This is where the concept of productive failure comes in.

What is Productive Failure?

Productive failure is the concept that struggling with a problem—and even failing to solve it initially—can lead to a deeper understanding and better long-term outcomes. The initial failure isn’t wasted effort; it creates the groundwork for insight by forcing us to test assumptions, push boundaries, and actively engage with the problem.

In education and research, productive failure has been shown to help learners build more durable skills. In GIS, the concept is just as powerful.

How Productive Failure Shows Up in GIS Work

Productive Failure

GIS professionals experience productive failure all the time—often without naming it:

Coordinate System Confusion: Misaligned datasets may initially seem like a frustrating setback. But wrestling with projections teaches you more about spatial reference systems than any tutorial could.

Parcel Fabric Adjustments: Struggling to reconcile overlapping deeds or inconsistent surveys often reveals how boundary data is historically imperfect—and trains you to work with both geometry and legal nuance.

Data Model Missteps: Building a geodatabase the “wrong way” first can help you see why topology rules, domains, and subtypes matter, leading to stronger schema design next time.

Geoprocessing Failures: A buffer tool crashing or returning unexpected results might push you to revisit parameters, attribute fields, or feature types—and that troubleshooting process strengthens your technical instincts.

Each of these examples demonstrates that the “failure” stage is often where real learning occurs.

Why GIS Professionals Should Lean Into Failure

Deeper Understanding – By troubleshooting errors, you’re not just memorizing steps—you’re learning why GIS works the way it does.

  • Problem-Solving Mindset – GIS is as much art as science; failed attempts sharpen your ability to think flexibly and creatively.

  • Resilience in Projects – Not every dataset or workflow will cooperate. Being comfortable with setbacks makes you more adaptable when managing projects with messy data or shifting requirements.

  • Innovation – Many new methods or workflows in GIS come from failed attempts at conventional solutions. The willingness to fail opens space for new approaches.

Putting Productive Failure Into Practice

Document your missteps: Keep a troubleshooting log of what didn’t work and why. This is often more valuable than a list of “successful” steps.

  • Encourage experimentation: When training colleagues or new GIS analysts, let them test workflows before showing the “right” answer.

  • Shift perspective: Instead of asking, “How do I avoid mistakes?” ask, “What did this mistake teach me about my data or my tools?”

  • Share failures openly: Within GIS teams, normalize conversations about problems encountered. They’re often more instructive than polished project showcases.

Conclusion

GIS is inherently iterative—layers don’t line up, data doesn’t reconcile, and tools sometimes fail spectacularly. But instead of viewing these setbacks as wasted time, we should recognize them as essential parts of our growth. Productive failure is what transforms GIS professionals from tool operators into problem-solvers, innovators, and true spatial thinkers.

The next time your parcel fabric refuses to balance or your spatial join won’t run, remember: that frustration may be the most productive part of your learning process.

Panda Consulting welcomes MIkki Conkling to our Team.

We are thrilled to announce the newest addition to the Panda Consulting team: Mikki Conkling! Please join us in welcoming Mikki as our new Geospatial Data Analyst.

Mikki brings experience in data research, attention to detail, and analysis to our team. She is passionate about leveraging data to drive meaningful insights. With her sharp analytical skills and dedication to excellence, we are confident that Mikki will be pivotal in advancing our geospatial data capabilities and helping our clients make informed decisions.

Her commitment to innovation and problem-solving perfectly matches our values here at Panda Consulting. We are confident she will fit in well and enhance our team culture. We cannot wait to see her impact on our projects.

Welcome aboard, Mikki! We are thrilled to have you join the Panda Consulting family. Let's embark on this exciting journey together!

Panda Consulting Receives the Esri Parcel Management Specialty Designation

Panda Consulting is excited to announce that Esri has recognized us with the Parcel Management Specialty designation.

As Esri notes on the partner pages, “As a partner in the Parcel Management Specialty, Panda Consulting is recognized for your expertise in leveraging ArcGIS Parcel Fabric to map land rights, restrictions, and responsibilities. You have expertise in property recording and registration workflows, integration with computer-assisted mass appraisal (CAMA) systems and deliver solutions and services to implement ArcGIS Parcel Fabric for managing, editing, and sharing property and parcel information.” 

If you are interested in the Parcel Fabric and learning how to better manage and maintain your Land Records, please reach out to us and we can setup a meeting to discuss your needs.

Panda Consulting Introduces its YouTube Page

Panda Consulting is proud to introduce its Panda Consulting YouTube page containing videos from our Workshop Series and compiled over the years. This page will make access to these videos more open and easier to get to. In addition, the YouTube page will allow viewers to comment and request topics that they would like us to explore in the Workshop series.

We hope you enjoy the videos and feel free to provide us with feedback.

We are here for you.

The impact from the Coronavirus (covid-19) is still unknown, but it has forced each of us to face challenges that none thought possible just a few months ago.

As we face the uncertainty of the current moment, one thing we know for sure - we’re all in this together.

We at Panda Consulting, having converted to remote working almost 10 years ago, are sensitive to the issues that you face working remotely and being disconnected from the usual social and community interaction. We wish to assure everyone that we not only know how to overcome the challenges, we are here to help you as you face them.

Whether we have helped you in the. past and are friends for years, or we are friends that have not met, please do not hesitate to help us keep this community strong.

To help everyone, we are planning on having a series of free seminars in the coming months to help keep you informed and in touch with others and will post news of those as they are scheduled.

Please think of us as a resource and reach out for anything that you might need: whether it is a problem mapping certain problem parcels, helping to keep up with the backlog or just wanting to stop for a moment and talk to someone - Please reach out to us.

Panda Consulting Welcomes Chris Conkling

Panda Consulting is proud to announce that Chris Conkling has joined our team as Geospatial Technician. Chris is a proud graduate of the University of Central Florida in Orlando, Florida and has a Bachelors of Arts degree in Philosophy with a minor in Film Studies.

While still attending the University of Central Florida, Chris applied to, and was hired by Apple, becoming an integral part of the operation from specialist to technical expert.

During his time at Apple, Chris provided Leadership functions, technical support and expertise, coordinated Business Leads, and taught many one -on-one training sessions, workshops, and core training sessions. 

Chris has been surrounded his entire life with GIS and will be assuming the traditional responsibilities of a geospatial technician as well as attending conferences to network and get to know our Clients. In addition to providing all-around technical assistance, Chris will be focusing on new technologies (think ArcGIS Pro and ArcGIS Online) and developing additional training and support opportunities.

Please take some time and welcome Chris and ask him about his experiences at Panda Consulting.  More biographical information is found here.

A Discussion on Computer Resources when Moving to the ArcGIS Parcel Editing Solution (the Parcel Fabric)

Executive Summary

The Parcel Fabric technology behind ESRI’s Parcel Editing Solution, differs from the standard feature classes used within ESRI’s geodatabases in many ways. The Parcel Fabric, looking to develop a more structured and integrated land records solution, incorporates all the traditional thematic layers used by land records, together with auxiliary  functional feature classes to provide a more complete solution that provides for creation, maintenance, history, metadata and adjustment layers required in a production environment to ensure the “mappers” have at their immediate disposal a complete resource for cadastralists. This structure, while being optimized for land record maintenance places a much more rigorous demand on computer resources. This short discussion will explore some of the demand points.

Integrated Feature Classes

The Parcel Fabric, in order to integrate the various thematic layers and make the validation of “topology” between the traditional features, manages the features differently. Rather than maintaining a multitude of feature classes, each having separate. discrete thematic feature classes, groups all features in the Parcel Fabric by geometry type, or “the type of geometric elements they represent such as polygon areas, line features and point features” rather than “the type of geometric features that represent, such as PLSS Township, Sections, Subdivisions, Lots, Tax Parcels, Encumbrances and Other areas, along with each layers corresponding lines and points”.  By reducing the number of feature classes included in the Parcel Fabric, it simplifies the structure, ensuring all features share the same spatial reference and connectivity, but using attribution to differentiate between the elements they represent.

This unification of geometry types complicates the search and display operations of the Parcel Fabric by having a greater number of features that must be searched through for record retrieval.  This integration is one reason why the creation, optimization and constant maintenance of the spatial indices with the feature dataset containing the Parcel Fabric is critical.

Relational Data Structure

Within the Parcel Fabric, all geometric feature classes, together with additional auxiliary operation feature classes and tables, are related to one another.  The Parcel Fabric can be thought of as a “geometric network” for  polygons.  Each polygonal record contains a complete set of lines that were used to create the polygon boundary, together with a corresponding record in the plan table containing the source data metadata and relates to all corner points that contain information about how the polygon corners are “linked” or “joined” together to define the spatial location and geometry of the polygon. As such, operations requiring the retrieval of a single record requires that that single record, and all related features must be retrieved to provide the Cadastralist with necessary information of every element related to that polygon. This intensified retrieval of single, al all related records places a much greater demand on the ability of the Parcel Fabric to index, search and retrieve the database records.

Editing Integrated Records

Because all records in the Parcel Fabric are related to corresponding line and corner records, editing the Parcel Fabric in a multi-user editing environment such as ESRI’s SDE versioning environment is highly transactional.  Within the SDE editing environment all changes to the tables, including adding records, deleting records or modifying records place “temporary” records in the “Change or Delta” tables that represent the “pre-committed”, or “posted”, data changes.  Since all records have these multitude of of related data associated with them, the Parcel Fabric will create or delete these associated features every time any change occurs to a polygonal record. For example, a simple modification of the location of a single point requires that all polygons, including polygons that are considered on other “layers” such as PLSS layers, subdivision layers, lot layers, easement layers, along with those lines connected to that corner, must be deleted from the Change table and added back into the change table to reflect that one simple move.  While that one simple move in a simple feature class may be represented by a delete and an add, in the Parcel Fabric, this one change may be represented by 30 or so deletes and 30 or so adds into these same Change tables. The more the data is edited in the Parcel Fabric, the larger and more cumbersome the Change tables become.  

For this reason, ESRI restricts the levels of versioning in the Parcel Fabric to only one level and highly recommends that maintenance on the Change tables be performed daily using the “analyze” geoprocessing tool to reduce and compress the number of redundant “state’ records contained in the Change table.  ESRI also recommends that all versions be reconciled and posted to the Default database state as quickly as possible.

Possible Implementation Scenarios

Taking into consideration the impact of the Parcel Fabric on the operations of the enterprise Geodatabase, there are several implementation recommendations.  

Segregated Implementation - The purpose of the Parcel Fabric is solely the creation, maintenance and production of land record information and the publication of this data should NEVER be performed from this highly integrated data structure (the Parcel Fabric). Rather, the data should be extracted, transformed and loaded into a publication data structure, while this implementation is often performed on the same server, just into separate feature datasets, one alternate suggestion some of our clients have taken is to segregate the entire Parcel Fabric structure and the geodatabase containing the Parcel Fabric onto a separate database server. The exact configuration and implementation strategy is completely depend upon the organization's infrastructure and deployment strategy.

Optimized Hardware - Since the Parcel Fabric technology is highly transactional in nature, optimization of Input / Output is critical to success. This points to the recognition that much of the demand of resources for the Parcel Fabric in a multi-user database is not computational, but is the increased demand on the searching and retrieval of all the related records contained with the Parcel Fabric.  We have had several clients successfully realize the greatest return on investment by configuring the data server sufficient memory and with solid state drives to optimize the I/O functions contained therein.

Summary

Governmental agencies using taxpayer funds to pay for their internal systems need to justify expenditures, but, in the case of the Parcel Fabric, it often makes more sense to spend additional funds to optimize the IT configuration for the use of the Cadastralists.