Read cofounder Muhammad Umar's memo, Compression and Reinflation
CodeNinja AtomsUnited StatesSaudi ArabiaPakistan

Sector · Agriculture and earth observation

Physical AI for agriculture and earth observation

Farms, irrigation and land use are watched by sensors, satellites and aircraft, but the readings, the licences and the field records usually sit in separate systems. These are the questions engineers ask first, answered from 4 published CodeNinja Atoms reference architectures.

  1. What does a physical AI system for agriculture and earth observation look like?
  2. Which AI models can an agriculture and earth observation operator run on its own hardware?
  3. How much compute and hardware does AI in agriculture and earth observation need?
  4. Is it cheaper to own AI hardware or rent cloud GPUs in agriculture and earth observation?
  5. What ontology or object model does an agriculture and earth observation AI system need?
  6. Who approves the decisions an AI system makes in agriculture and earth observation?

What does a physical AI system for agriculture and earth observation look like?

A complete physical AI design for agriculture and earth observation names what to sense, which existing systems to join, the object model that joins them, the models and hardware, the three-year cost and the person who approves every action. CodeNinja Atoms has published 4 such reference architectures for agriculture and earth observation, each free to reuse under CC BY 4.0.

DesignCountryWhat it does
Field LedgerPakistanone dashboard that joins a farm's live sensor feeds, its historical datasets and a big data and analytics repository into one object model, so any farm, crop cycle or season can be drilled into, exported and reported on under role-based access.
BaselineUnited Statesone summer flight of 3-inch 4-band orthoimagery and USGS Quality Level 1 LiDAR, with every tile, point cloud and elevation model bound into a site ontology, so the next season starts from a comparison instead of rediscovery.
Fodder WatchSaudi Arabiaan 18-month earth observation service that screens every parcel for restricted green fodder and cultivation beyond the licensed area, checks each detection against the holding's licence, and turns the confirmed ones into case files an inspector can act on.
A Self-Improving AI System for Canal Irrigation Water Allocation in PakistanPakistanAn open reference architecture for a self-improving AI system in physical AI, built for a provincial irrigation department in Pakistan that takes its share of river water at barrages and head regulators and delivers it through a main canal, distributaries and minors to outlets farmers share by rotation, where owning the inference hardware that runs it costs about 636,000 US dollars over three years. When a head regulator reading drops below its indent for three days at peak demand, the design joins the telemetry, the indent and release ledgers, the rotation schedule, the gauge reader's diary, the complaint register and the revenue crop records into one entitlement versus delivery argument, so the divisional engineer sees which reach is silted, which branch is over drawing and which gate adjustment cured the matching shortfall last season. Every model runs on the department's own hardware inside Pakistan under the inter provincial water accord, canal and drainage law, the national data rules for farmer records and export control on the GPU node.

Which AI models can an agriculture and earth observation operator run on its own hardware?

Each published agriculture and earth observation design names its models and why, and every model is open-weight or no model is used at all, so the operator can run it on hardware it owns.

DesignModels
Field LedgerNone: the analytics are deterministic aggregations, drill-down and reporting
BaselineNone: vegetation analysis stays with the operator's own analysts
Fodder WatchRF-DETR fine-tuned per region and Chronos-2 zero-shot, both Apache-2.0, about 0.55 GB of weights together
A Self-Improving AI System for Canal Irrigation Water Allocation in PakistanFrontier class open weights for the three drafting agents (shortfall, indent and dispute) and the command centre, self hosted for sovereignty; the operator names GLM 5.3 and the plan holds its FP8 arithmetic, but no weights are committed until the register verifies a model live; embedding, OCR and forecasting model classes for retrieval, handwritten Urdu and English ledgers and shortfall detection; no third party model service, nothing trained into weights
DesignChoiceWhat was pickedWhy
Field LedgerModelZero models committed; a forecaster over sensor time series stays open work gated on Milestone 1 evidenceThe requirement commits aggregations, drill-down and reporting, and no model was verified for this run
Field LedgerHardware classNo compute procured; all compute runs on operator-provided servers, storage and connectivityThe operator provides the hosting infrastructure and the sensors already generate the data, so no field compute or inference server is bought
Field LedgerSizing ruleDatabase and buffer sizing set against the recorded server specification at the Milestone 1 kick-off, re-estimated on measured sensor volumes before full-farm integrationSensor formats, volumes and refresh rates are settled by the prototype, not assumed at bid time
Field LedgerSensingThe operator's existing sensor devices, read-only; no cameras and no new field hardwareThe world is sensed by farm rather than watched, and the engagement installs no equipment
Field LedgerPatternSystem of Context, with the ontology as a versioned schema and mapping projection inside the databaseFarm, field, crop cycle, sensor device and dataset objects answer the cross-system questions no single source can
Field LedgerGroundOpen-source PostgreSQL with PostGIS, on operator premises in Pakistan, under permissive and copyleft open-source licensesThe open-source database mandate and the source code and intellectual property transfer make the operator the owner of every artefact
BaselineLearned modelNone; the model register is empty by decisionNo agent or model layer was wanted; vegetation analysis stays with the operator's own staff in its own tools
BaselineLicense positionNo model license exists to hold or triggerWith zero weights, ownership runs through the professional services agreement, not through a license
BaselinePositioning classGNSS guidance and correction service, with network RTK or an owned base stationQuality Level 1 accuracy is decided by this chain, so it is specified by baselines, correction source and test evidence
BaselineAcquisition platformManned aircraft with a 4-band red, green, blue and near-infrared large-format cameraUnmanned data will not be considered, so the acquisition class is fixed by the requirement
BaselineLiDAR sensingQuality Level 1 sensor at a minimum 8 pulses per square meterThe 16 pulses per square meter option is priced separately and exercisable at the operator's option
BaselinePattern the design stands onSystem of Context, with the ontology as a projection over the systems of recordDeliverables carry flight mission, sensor and processing provenance, so analysis joins to units, missions and seasons rather than to tiles
BaselineGround it runs onThe operator's ArcGIS Enterprise environment in the United StatesFiles are publish-ready, and publication stays with the operator's own GIS staff inside its own boundary
Fodder WatchDetectorRF-DETR, Apache-2.0, fine-tuned per region, BF16, about 61 to 68 MB at 16 bitNo field-of-use restriction, so the operator owns the fine-tuned weights outright
Fodder WatchForecasterChronos-2, Apache-2.0, zero-shot, about 120M parameters, FP32, about 0.48 GBThousands of independent per-parcel index series with no fine-tuning dependency
Fodder WatchCheckpoint exclusionsRF-DETR XL and 2XL under Roboflow's Platform Model License, excludedField-of-use terms would compromise in-Kingdom weight ownership
Fodder WatchInference node48 GB PCIe GPU class (L40S class), air-cooled, in the sovereign facilityFootprint rule: combined weights under 0.55 GB leave batch and cache headroom
Fodder WatchPositioningRTKLIB class GNSS with optional site base station, field tablets at 3 to 5 m gradeArrival coordinate checked against the flagged polygon, so phantom visits file as not-reached
Fodder WatchOptical sensingSentinel-2 multispectral, 10 m, 5-day revisitResolves center pivots for crop class without a foreign processing dependency
Fodder WatchRadar sensingSentinel-1 C-band SARCloud-proof complement; dust and haze, not cloud, are the optical channel's real attacker
Fodder WatchArchive sensingLandsat 8/9, 8-day combined, archive reaching back decadesHistory for per-parcel baseline series
Fodder WatchCloud evidenceSentinel-2 scene classification and cloud probability layerTreated as evidence, not truth, in the screening rule
Fodder WatchAerial sensingnational aerial survey productsRounds over the sedimentary shelf, matching the operator's existing method
Fodder WatchField truthGNSS field tablets on inspector visitsConfirmed and refuted visits become the labelled corpus for each season's retraining
Fodder WatchPattern: triagePer-parcel signature time series with traffic-light triageOnly the flagged minority reaches a human inspector
A Self-Improving AI System for Canal Irrigation Water Allocation in PakistanReasoning model (frontier work surface)Frontier class open weights, self hosted for sovereignty, Kimi class; the operator names GLM 5.3 and the plan holds its arithmetic (published FP8 weights of about 756 GB on one 141 GB class node of eight GPUs with about 280 GB of KV cache headroom), but no weights are committed until the register verifies a model liveThe operator holds the weights and no third party model service ever touches canal data; no open weight model was verified live on this run, so the row stands as a class and the GPU count follows only when a verified model stands in the register
A Self-Improving AI System for Canal Irrigation Water Allocation in PakistanEmbedding model classEmbedding models for retrieval, by role rather than name, on the 48 GB PCIe class site serverProject ledger text and telemetry annotations into the retrieval space the three drafting agents search; licence terms attach to the register row when a named model at a named version stands
A Self-Improving AI System for Canal Irrigation Water Allocation in PakistanOCR model classOCR models for the handwritten Urdu and English paper ledgers, on the 48 GB PCIe class site serverEvery batch passes a human verification stage with a 2 percent failure gate before anything enters the object model, because a wrong entitlement baseline would corrupt every downstream comparison; OCR corrections are a verification stage, not a training set
A Self-Improving AI System for Canal Irrigation Water Allocation in PakistanForecast model classForecasting models for shortfall detection, on the 48 GB PCIe class site serverShortfall detection must land inside one telemetry cadence so a developing head shortfall is visible on the first of the three days it takes to breach; modest, continuous work that must survive independently of whatever the frontier layer becomes
A Self-Improving AI System for Canal Irrigation Water Allocation in PakistanFrontier hardware141 GB HBM GPU class, one node of eight GPUs (about 1,128 GB of aggregate memory)The held arithmetic fits about 756 GB of FP8 weights with about 280 GB of KV cache headroom; the node sits above the US advanced computing export threshold for Pakistan, so the export licence determination runs first in phase one with an in country procurement route or colocation fallback named before any order
A Self-Improving AI System for Canal Irrigation Water Allocation in PakistanSite server hardware48 GB PCIe class site server beside the frontier node, in the circle server roomLedger digitisation and shortfall detection need modest, always on compute chosen by class; no edge tier, nothing served at a canal head in phase one
A Self-Improving AI System for Canal Irrigation Water Allocation in PakistanFrontier footprint sizing ruleFrontier model GPU footprint sizing rule, vLLM and SGLang serving runtimesOpen serving runtimes sized against the weights and the KV cache ceiling on hardware the operator owns
A Self-Improving AI System for Canal Irrigation Water Allocation in PakistanNode count ruleGLM 5.3 node count by GPU class: one 141 GB class node at FP8Chosen against GLM 5.3 at BF16 on two nodes or a mid size model; conditional until the register verifies
A Self-Improving AI System for Canal Irrigation Water Allocation in PakistanServing runtimevLLM and SGLangServe the FP8 weights within the KV cache ceiling the sizing reserves once a verified model stands
A Self-Improving AI System for Canal Irrigation Water Allocation in PakistanRegistryHarbor, air gapped artifact and model registryModel and container updates enter as staged, versioned artifacts, verified before promotion; a failed or suspect update leaves the previous version serving
A Self-Improving AI System for Canal Irrigation Water Allocation in PakistanSensingCanal head flow depth and velocity telemetry, inter provincial point telemetry, route based gauge reader readings, complaint register entries, digitisation verification checksLive flow at the heads, the manual baseline in the field, and the human check that gates OCR into the ontology; no cameras and no new field hardware
A Self-Improving AI System for Canal Irrigation Water Allocation in PakistanPattern: memoryMemory of confirmed causes and accepted adjustments, nothing trained into weightsThe operator requires improvement every rotation without training a model on the fly; only what a named engineer confirms at the decision compounds, captured then and not reconstructed
A Self-Improving AI System for Canal Irrigation Water Allocation in PakistanPattern: validationManual and telemetry baselines taken together in the first month and reconciled in the openA comparable irrigation automation program found its computed efficiency fell once continuous measurement exposed manual under measurement, so no improvement is claimed before the baselines agree
A Self-Improving AI System for Canal Irrigation Water Allocation in PakistanPattern: ontology firstThe governed canal network ontology reconciled against one real week of telemetry and ledgers before any agent draftsPhase one's exit gate is the ontology itself, proven on one main canal for one cropping season before extension to the other canals
A Self-Improving AI System for Canal Irrigation Water Allocation in PakistanPattern: boundaryThe operator's own hardware in the circle server room, Pakistan; read only adapters; no gate actuation; no third party model serviceTelemetry and ledger data never leave the network, open weights on owned hardware, and every physical action keeps its existing owner under canal and drainage law and the department's gate procedures

How much compute and hardware does AI in agriculture and earth observation need?

The compute follows from the models: the published agriculture and earth observation designs size it as follows, from no new hardware to a full GPU node.

DesignPartThe design
Field LedgerStackOpen-source PostgreSQL with PostGIS on the operator's own servers; source code and full intellectual property handed over
BaselineGroundThe operator's ArcGIS Enterprise; nothing runs in a cloud the operator does not control
BaselineAcquisitionOne manned flight within a week either side of 1 July; 3-inch 4-band (red, green, blue, near infrared) orthoimagery and Quality Level 1 LiDAR at a minimum of 8 pulses per square meter
Fodder WatchComputeOne 48 GB L40S-class inference node inside the Kingdom; the card class needs a US export licence
A Self-Improving AI System for Canal Irrigation Water Allocation in PakistanComputeOne node of eight 141 GB HBM cards (about 1,128 GB) in the department's circle server room, the held arithmetic for about 756 GB of FP8 weights, beside a 48 GB PCIe class site server for the small model tier; no edge tier, nothing served at a canal head. The node sits above the US advanced computing export threshold for a D:2, D:3 and D:4 destination, so the export licence determination runs first in phase one with an in country procurement route or colocation fallback named before any order

Is it cheaper to own AI hardware or rent cloud GPUs in agriculture and earth observation?

Each agriculture and earth observation design prices three years of ownership in its Appendix A, with every price cited, against renting the same capacity from a cloud region at its deepest three-year commitment where hardware is bought.

DesignLineThree years
Field LedgerThree-year costNo hardware line to price: the cost is the integration and software work (Appendix A)
BaselineThree-year costNo compute to price; the acquisition is priced by the survey firm against the operator's own task table (Appendix A)
Fodder WatchThree-year costAbout 15,200 dollars to own the node, about two thirds the deepest three-year AWS commitment, and renting would move the data outside the Kingdom (Appendix A)
A Self-Improving AI System for Canal Irrigation Water Allocation in PakistanThree-year costAbout 636,000 US dollars to own the frontier node and the site server for three years (a range of 606,000 to 662,000: servers, support and power at the national uniform tariff), against about 773,000 to rent the same eight 141 GB cards and one 48 GB card on the deepest three year commitment in AWS Asia Pacific (Mumbai), so ownership costs about four fifths of it, and about 2.05 million on demand, against which ownership costs a little under a third. Renting is a price reference only, because AWS lists no region in Pakistan and every rented option would carry telemetry and ledgers across the border; the frontier footprint itself stands only when the register verifies a model (Appendix A)

What ontology or object model does an agriculture and earth observation AI system need?

The object model is the part that makes the system an ontology rather than a pipeline: typed objects for the things in the agriculture and earth observation operation, with properties, status values and typed links. Every published design ships its object model as hyper-ontology/1 JSON that loads into Hyper Ontology.

DesignSizeObjectsDownload
Field Ledger12 objects, 12 linksFarm Site, Field, Crop Cycle, Sensor Device, Sensor Reading, Historical Dataset, Publication, Dashboard User, Access Role, Alert, Report, Data Source Connectionobjects.json
Baseline16 objects, 14 linksMapping Site, Land Unit, Watercourse, Dam, Flight Mission, 4-Band Aerial Camera System, QL1 LiDAR Sensor System, GNSS/IMU Georeferencing Chain, Multispectral Orthoimagery Product, Classified LAS Point Cloud, Bare-Earth and Highest-Hit DEMs, QA/QC Accuracy Report, Professional Services Agreement, Monthly Itemized Invoice, Contractor Project Manager, Operator Project Managerobjects.json
Fodder Watch14 objects, 14 linksFarm holding, Centre pivot / cultivated field, Farm enterprise / large farmer, Crop licence (wheat / seasonal fodder), Water source (well) use licence, Green fodder ban control, Agricultural fuel / electricity service condition record, Imagery tasking order, Satellite image capture, Processed imagery product, Restricted-crop detection flag, Violation case file, Field inspector, Restricted-crop classifierobjects.json
A Self-Improving AI System for Canal Irrigation Water Allocation in Pakistan16 objects, 13 linksBarrage, Head regulator, Reach, Gate, Outlet, Main canal, Distributary, Rotation, Shortfall, Season, Indent, Release, Complaint, Crop area, Telemetry reading, Gauge readingobjects.json

Who approves the decisions an AI system makes in agriculture and earth observation?

In every published agriculture and earth observation design a named person makes the decision that changes the physical world; the system prepares it.

DesignHuman control
Field LedgerEvery alert is acknowledged by a named user under a role the operator assigns
BaselineThe operator's project manager accepts each deliverable against the QA/QC accuracy report
Fodder WatchEvery flag is verified on the ground by a named field inspector before a case file opens
A Self-Improving AI System for Canal Irrigation Water Allocation in PakistanAgents draft and people decide, by name: the controlling engineer confirms or rejects the drafted cause and correction before any gate instruction is drafted, the indent draft is approved before it goes to the national authority, and the dispute account is drafted from cited records for the officer to send; the gate stays a hand operation on telephone instructions, and every confirmed cause and accepted adjustment is kept as memory the next season reads

Every answer on this page is drawn from the papers linked in it: each paper's At a glance table, model register and cost appendix. Full text for agents: llms-full.txt. Designed on Praxis; object models load into Hyper Ontology.

Want one of these designs for your own operation? Talk to us.