two bodies — a note by the sea

v6 · updated 2026-11-03 · the sea's maps, the body's long stories, the night

A live audiovisual essay that places two bodies side by side — the Baltic Sea and the artist's — each continuously measured by instruments, and listens to the gap between the number and the felt.

The number and the felt

The piece pairs what can be computed in two bodies with what cannot: what these phenomena mean, and why they matter. Who is the body that observes and feels these data? The instruments measure; the artist's voice speaks the subjectivity — words for what no sensor computes, yet still a reflection of something real. Not a digital twin of the sea: a digital stepbrother. It reads the same data that feed the twin, but keeps a body in the loop — and words.

What you're seeing

Every five minutes, a small computer reaches out to the observation stations on Utö and at Tvärminne — at the edge of the Finnish archipelago, where the Baltic Sea begins to open. They ask: what is happening right now?

The stations answer in numbers. Water temperature. Salinity. Dissolved oxygen. Wave height. Wind speed and direction. How much light is reaching the surface. Whether the CO₂ in the water is rising or falling. Alongside them, ocean-model data from the Copernicus Marine Service.

These numbers enter a pipeline. A perceiver looks for what is noteworthy — trends, anomalies, threshold crossings — and assigns significance. A coupling perceiver then asks whether anything the sea is doing lines up with something the artist's body is doing, along a real physical mechanism: gas exchange, heat transfer, rhythm, osmosis, light, agitation, pressure.

An assembler then reaches into a small library of sentences the artist has already written — a somatic interview, an address-the-sea pool, ecology fragments — and surfaces the two or three that fit the moment. It does not generate the language. It surfaces what has been written.

The text appears over a sea rendered in your browser, word by word, in time with a voice. The same data that chose the words also drives the waves — their height, their speed, their direction.

The pipeline

Every five minutes two streams flow through the same machine. From FMI Utö and Copernicus Marine comes the sea: temperature, salinity, oxygen, waves, wind, chlorophyll, pCO₂, currents. From a Garmin watch on the artist's wrist comes the body: heart rate, breath, stress, sleep, body battery, blood oxygen, respiration.

Each stream has its own perceiver that asks what is noteworthy? — across four time scales (fast, diurnal, slow, seasonal), all detected by the same body-agnostic math. The two streams then meet in a coupling perceiver that reads a table of physical links — the actual physics that connect the two bodies. The sea and the body meet through these correspondences of metabolism — gas exchange, heat, rhythm — grounded in physical links; where data are missing, the piece stays silent.

An assembler — pluggable, no language model in the live pipeline — reads the ranked phenomena and the coupling state, and pulls sentences from three pools the artist maintains by hand: body state (first-person), address / contact (the observer's voice to the sea), and ecology fragments (impersonal standing context). It picks the person by distance, not by style. It does not compose. It surfaces.

sea data                           body data
(FMI Utö + Copernicus)             (Garmin via garth)
        │                                   │
        ▼                                   ▼
  sea_perceiver                      body_perceiver
  phenomena + significance           phenomena + significance
        │                                   │
        └───────────────┬───────────────────┘
                        ▼
            coupling_perceiver          ←   physical_links.yml
            difference · synchrony
            ratio  ·  distance  ·  contact
                        │
                        ▼
            context_builder   →   linkage_resolver
                        │
                        ▼
            RetrievalAssembler          ←   sea_register.yml   (you / we)
            fallback ladder             ←   body_voice.yml     (i)
            person by distance state    ←   ecology_fragments.yml
                        │
                        ▼
            narrator_output.json  →  web visualisation
            narrator_archive.json
            narrator_logs/<ts>.txt

The water

The water surface is a real three-dimensional mesh with wave displacement — swell driven by the live wave direction and height, plus a fluid simulation running in the browser that advects particles across it. Wind direction and speed drive the flow. Chlorophyll and phycocyanin tint the surface.

The sun and the moon are the real ones over Utö, for the actual time — the moon with its actual phase. One light level dims everything at night: the water's own colour, the foam, the bloom on the surface. At night the waves catch only a faint sky glow; when the moon is up it lays its glitter path; when it is new or below the horizon, it is honestly absent.

Maps, places, sensors

The Copernicus maps — temperature, chlorophyll, oxygen, pH, currents, waves — flow by their own structure: where the map is even it rests, where it has fronts it moves. Satellite images of real places — Helsinki, Rauma, Kotka, Åland, the Neva estuary, the Kiel and Mecklenburg Bights — are rebuilt from particles and set flowing in the Copernicus field of the same place on the same day, 14 July 2026, the day of the kayak trip. No place borrows another place's data. In a few shots the sea crosses the coast and lies over the still land: and what if the water would change direction and mind, and go back to the land where it comes from?

The kayak trip from Pargas to Nötö is replayed on its real GPS track, shedding ink. A descent follows one real water column south of Utö to the seabed. Two particle shots are seen by a sensor instead of by daylight — an x-ray, and an infrared coloured by today's sea temperature.

The data

Sea data comes from the Finnish Meteorological Institute's autonomous observation station on Utö (59.78°N, 21.37°E) — which has measured the Baltic Sea continuously since 1900 — from the coastal MoniCoast sondes at Tvärminne (surface to 30 m), from Copernicus Marine Service (models and satellites, surface to seabed) and from SYKE's daily Sentinel-3 true colour. A plausibility check silences a sensor whose readings stop making physical sense, rather than letting a fouled instrument speak. Body data comes from a Garmin activity tracker via the garth API — read from minutes to seasons: training, recovery, the energy a body charges and spends.

The Baltic Sea is a shallow, brackish inland sea under severe ecological pressure. Eutrophication, deoxygenation, warming, and changing salinity patterns are transforming it. The data this piece reads is not abstract — it is a record of a body of water in crisis, still alive, still speaking.

The voice — one voice, three persons

There is one voice in this piece: the observer's — the sea itself stays wordless, and so does the narrator-machine. The observer speaks in three grammatical persons meant as a distance scale rather than stylistic variation:

The three persons are meant as a reading of the distance between the observer and the sea — kilometres of separation, the difference in the weather above them, and being in the water. For now the observer's position is not yet tracked, so the distance is drawn by chance at each reading — the voice pretends to be far, near, or in the water. The sea itself stays wordless.

The narrator IS the field observer. The body enters as first-person condition, not as raw data. No heart-rate numbers appear in the text. The body shows up in sentences the artist wrote about it, surfaced when the moment fits.

The second body

Alongside the sea data, a second stream reads the artist's own body through the watch. A perceiver detects what is salient across the same four time scales as the sea. A coupling perceiver then asks whether any of it lines up with what the sea is doing along a real physical mechanism.

What the audience sees is not the body's numbers. It is the body's condition, in the artist's own words, surfaced when it connects to something the sea is doing. Two bodies — the sea and the observer — held next to each other where their metabolisms correspond.

The trips · the residencies · what makes the corpus

The library the assembler reads from is not curated code — it is the artist's own writing. It grows out of trips to the water: kayaking summers around the archipelago, residencies on Seili and Vartiosaara, long sessions of somatic interview back on land. Field notes and journal entries. Sentences said out loud while sitting on a rock and written down later.

Each residency deposits new material into a corpus directory in the piece. When a session on Seili produces the sentence my feet have memories of this temperature, that sentence enters the assembler's pool for the temperature parameter. It waits there, unchanged, until the sea's temperature does something the perceiver considers worth naming — and then it surfaces, next to whatever the sea is doing at that moment.

The piece therefore is not a snapshot. It is a slow accumulation of the artist's writing about the sea, published as the sea keeps changing. Every trip adds sentences. Every future composition can reach for them.

What's next · Phase 4

The current live pipeline is the retrieval assembler: it selects and juxtaposes existing sentences. The roadmap includes further phases that read the same corpus differently.

The most anticipated is Phase 4 — QLoRA: a small language model fine-tuned on the artist's own corpus. The QLoRA-adapted model would generate new sentences in the artist's voice, but constrained by the same physical-links table the assembler uses today. The fence stays. The model may only speak along mechanisms that actually connect the two bodies. What changes is that new language becomes possible on nights the corpus has already been fully read.

Phase 4 will not replace the retrieval assembler. It will run alongside it, reachable per shot: a shot where fidelity matters uses retrieval; a shot where discovery matters uses the fine-tuned model. When the model is training, the piece enters the dreaming state. When it has nothing new to say and the retrieval pool is dry, the piece rests until the next reading gives it something.

                phenomena + coupling + shot context
                                │
                                ▼
                       ┌──────────────────┐
                       │  ContextBuilder  │
                       │  n · weights ·   │
                       │  register · mode │
                       └────────┬─────────┘
                                │
        ┌───────────────┬───────┴───────┬────────────────┐
        ▼               ▼               ▼                ▼
   [ Phase 1 ]     [ Phase 2 ]     [ Phase 3 ]      [ Phase 4 ]
   Retrieval       Embedding       Cut-up          Generative
   yaml lookup     nearest-        clause-level    QLoRA on
   by phenomenon   neighbour       recombination   Roberto's
   + significance  in fragment     of the          corpus,
                   embedding       corpus          fenced by
                                                   physical_links
        │               │               │                │
        │               │               │                │
   ── LIVE ──       roadmap         roadmap          roadmap
                    (small model)   (needs corpus)  (autumn)
        │               │               │                │
        └───────────────┴───────┬───────┴────────────────┘
                                ▼
                       fragments juxtaposed
                       (no glue, reader connects)
                                ▼
                       narrator_output.json

Credits

Roberto Fusco — artistic direction, data pipeline, visualization, corpus

FMI (Finnish Meteorological Institute) — Utö station data since 1900

Tvärminne Zoological Station, University of Helsinki — MoniCoast sondes

Copernicus Marine Service — PHY, BGC, WAV, OLCI, SST

Sentinel-2: Copernicus Data Space Ecosystem (ESA) · Sentinel-3 true colour: SYKE Tarkka

Coastline: Natural Earth · sun and moon: SunCalc (V. Agafonkin, BSD-2)

Self-displacing maps after “molten bismuth” by Florian Berger (flockaroo), CC BY-NC-SA 3.0

Code written with Claude (Anthropic) as coding assistant

Built with WebGL / Three.js and a small Python pipeline. Runs on a Raspberry Pi every five minutes. Hosted on Infomaniak.

two bodies — a note by the sea is part of Roberto Fusco's ongoing artistic research into environmental data, embodied experience, and computational narration.