FlavoRotor is in developmentSee the current stage
FlavoRotor
Register interest
Research

Crop programmes · CROP-LET-001

Lettuce growth, forecasting and cultivation trials

Longitudinal biomass forecasting with leave-one-plant-out validation, independent multimodal datasets and cultivar-specific pH, nutrition, flavour and root-zone temperature trials.

MarkdownJSONRevised 2026-07-29
In brief

A genotype-specific programme for pH, nutrient strength, root-zone temperature and short pre-harvest flavour treatments.

Longitudinal lettuce growth

A growth model needs repeated measurements from the same plant. Karimzadeh and Ahamed's dataset links 18 identified lettuce heads to 30 daily biomass measurements, RGB canopy images and environmental readings. The sequence contains 540 biomass observations and 1,443 environmental records.

Figure 13

The same controlled cultivation study observed through time

Full-frame canopy images from four dates show why repeated, indexed imaging is more informative than unrelated photographs.

Values
SeriesValueNote
Day 1 after transplantPublished full-frame RGB canopy imageSource file aalto-canopy-01.png. The complete frame is shown without synthetic content or symptom editing.
Day 15 after transplantPublished full-frame RGB canopy imageSource file aalto-canopy-02.png. The complete frame is shown without synthetic content or symptom editing.
Day 27 after transplantPublished full-frame RGB canopy imageSource file aalto-canopy-03.png. The complete frame is shown without synthetic content or symptom editing.
Day 31 after transplantPublished full-frame RGB canopy imageSource file aalto-canopy-04.png. The complete frame is shown without synthetic content or symptom editing.

Note. Original RGB canopy frames from Karimzadeh and Ahamed (2025), CC BY 4.0. Files are resized without cropping; hashes and source filenames are recorded in summary.json.

Figure 14

Fresh-biomass trajectory across 18 identified lettuce heads

The line is the daily mean. The shaded band spans the observed minimum and maximum, so biological spread remains visible.

050100150200250 Fresh biomass (g) 151015202530 Day after transplant meanobserved range
Values
SeriesValueNote
Day after transplant 1Mean 3.37 g · range 0.90–5.80 g18 individually identified lettuce heads; standard deviation 1.11 g.
Day after transplant 2Mean 7.98 g · range 5.60–10.20 g18 individually identified lettuce heads; standard deviation 1.13 g.
Day after transplant 3Mean 9.62 g · range 7.10–11.90 g18 individually identified lettuce heads; standard deviation 1.15 g.
Day after transplant 4Mean 10.29 g · range 8.10–11.80 g18 individually identified lettuce heads; standard deviation 1.06 g.
Day after transplant 5Mean 12.84 g · range 9.90–15.10 g18 individually identified lettuce heads; standard deviation 1.28 g.
Day after transplant 6Mean 15.62 g · range 11.70–17.90 g18 individually identified lettuce heads; standard deviation 1.56 g.
Day after transplant 7Mean 18.61 g · range 13.80–21.90 g18 individually identified lettuce heads; standard deviation 2.10 g.
Day after transplant 8Mean 21.97 g · range 15.70–26.50 g18 individually identified lettuce heads; standard deviation 2.78 g.
Day after transplant 9Mean 26.22 g · range 18.80–32.00 g18 individually identified lettuce heads; standard deviation 3.62 g.
Day after transplant 10Mean 31.04 g · range 21.60–38.60 g18 individually identified lettuce heads; standard deviation 4.62 g.
Day after transplant 11Mean 35.73 g · range 24.90–44.30 g18 individually identified lettuce heads; standard deviation 5.31 g.
Day after transplant 12Mean 40.39 g · range 27.70–50.10 g18 individually identified lettuce heads; standard deviation 6.15 g.
Day after transplant 13Mean 45.83 g · range 31.40–56.80 g18 individually identified lettuce heads; standard deviation 7.19 g.
Day after transplant 14Mean 52.42 g · range 35.50–66.30 g18 individually identified lettuce heads; standard deviation 8.52 g.
Day after transplant 15Mean 60.26 g · range 40.50–76.50 g18 individually identified lettuce heads; standard deviation 9.89 g.
Day after transplant 16Mean 69.14 g · range 47.80–87.50 g18 individually identified lettuce heads; standard deviation 11.12 g.
Day after transplant 17Mean 77.84 g · range 53.40–98.10 g18 individually identified lettuce heads; standard deviation 12.53 g.
Day after transplant 18Mean 84.34 g · range 57.80–105.90 g18 individually identified lettuce heads; standard deviation 13.35 g.
Day after transplant 19Mean 93.19 g · range 64.30–118.30 g18 individually identified lettuce heads; standard deviation 14.78 g.
Day after transplant 20Mean 100.55 g · range 69.60–127.10 g18 individually identified lettuce heads; standard deviation 15.66 g.
Day after transplant 21Mean 108.53 g · range 74.90–136.80 g18 individually identified lettuce heads; standard deviation 16.51 g.
Day after transplant 22Mean 114.84 g · range 78.10–145.10 g18 individually identified lettuce heads; standard deviation 17.53 g.
Day after transplant 23Mean 120.74 g · range 83.10–151.70 g18 individually identified lettuce heads; standard deviation 18.19 g.
Day after transplant 24Mean 127.14 g · range 86.30–160.00 g18 individually identified lettuce heads; standard deviation 18.89 g.
Day after transplant 25Mean 134.46 g · range 92.10–168.50 g18 individually identified lettuce heads; standard deviation 19.41 g.
Day after transplant 26Mean 141.40 g · range 96.20–177.90 g18 individually identified lettuce heads; standard deviation 20.67 g.
Day after transplant 27Mean 146.19 g · range 99.60–182.80 g18 individually identified lettuce heads; standard deviation 21.20 g.
Day after transplant 28Mean 141.69 g · range 98.40–174.40 g18 individually identified lettuce heads; standard deviation 20.05 g.
Day after transplant 29Mean 148.21 g · range 104.30–182.60 g18 individually identified lettuce heads; standard deviation 20.56 g.
Day after transplant 30Mean 152.84 g · range 109.30–186.30 g18 individually identified lettuce heads; standard deviation 20.73 g.

Note. 540 non-destructive biomass observations from Karimzadeh and Ahamed (2025): 18 plants × 30 days. Dates in the workbook differ from the repository description; analysis therefore uses day after transplant.

The mean fresh biomass rises from 3.37 g on day 1 after transplant to 234.56 g on day 30. The figure also retains the daily minimum and maximum, because a mean alone hides variation between plants.

Three-day biomass forecast

The forecast uses the most recent five daily masses to estimate biomass three days later. Three models are evaluated on the same 414 cases: persistence carries the latest mass forward; a five-day line extrapolates the local trend; ridge autoregression uses five masses, four daily mass increments and day after transplant.

Each outer fold withholds one complete plant. The ridge penalty is selected inside the training fold by withholding each of the remaining plants in turn. Measurements from the evaluated plant therefore cannot choose its coefficients or regularisation strength.

Figure 15

Three-day biomass forecast tested on plants withheld from fitting

Every method predicts the same 414 plant-days. Error bars are plant-cluster bootstrap 95% intervals for mean absolute error.

Values
SeriesValueNote
PersistenceMAE 17.20 g · RMSE 18.47 gThe latest measured mass is carried forward for three days. Plant-cluster bootstrap 95% interval for MAE: 16.03–18.31 g.
Five-day linear trendMAE 5.56 g · RMSE 6.86 gA straight line fitted to the five most recent measurements is extrapolated three days. Plant-cluster bootstrap 95% interval for MAE: 5.02–6.07 g.
Ridge autoregressionMAE 2.89 g · RMSE 3.67 gFive masses, four daily increments and day after transplant enter the model. Each plant is withheld in turn; ridge strength is selected only from the remaining plants. Plant-cluster bootstrap 95% interval for MAE: 2.67–3.10 g.

Note. Leave-one-plant-out outer validation; ridge strength chosen by nested leave-one-plant-out validation among the remaining plants. Generated by scripts/analyze-plant-monitoring-evidence.py.

ModelMAERMSEMAPER²
Persistence17.20 g18.47 g24.50%0.8378
Five-day linear trend5.56 g6.86 g8.07%0.9777
Nested-CV ridge autoregression2.89 g3.67 g4.18%0.9936
GRW-MAE
MAE=1n∑i=1n∣yi−y^i∣\mathrm{MAE}=\frac{1}{n}\sum_{i=1}^{n}\left\lvert y_i-\hat y_i\right\rvert
Mean absolute error is the average absolute difference between measured and forecast fresh biomass.

ExplanationMean absolute error averages the absolute distance between measured and forecast fresh biomass.

GRW-RMSE
RMSE=1n∑i=1n(yi−y^i)2\mathrm{RMSE}=\sqrt{\frac{1}{n}\sum_{i=1}^{n}\left(y_i-\hat y_i\right)^2}
Root mean squared error gives more weight to large forecast errors.

ExplanationRoot mean squared error squares each forecast error before averaging, so a small number of large errors have greater influence.

The ridge model reduces mean absolute error by 83.2% relative to persistence and by 48.0% relative to the five-day linear trend. Its plant-cluster bootstrap 95% interval is 2.67–3.10 g. This benchmark measures interpolation within one published cultivation study. A FlavoRotor growth model is re-evaluated by crop, cultivar, camera geometry and cultivation cycle.

How the forecast is used

The forecast creates an expected mass and an uncertainty range for the next observation. A measured plant that repeatedly falls outside that range is inspected together with its image sequence, pH, EC, light, temperature, dose history and root-zone record. The residual identifies an unusual trajectory; it does not name the cause by itself.

GRW-RES
et+h=yt+h−y^t+he_{t+h}=y_{t+h}-\hat y_{t+h}
The forecast residual is measured biomass minus predicted biomass at horizon h. Its sign and persistence show whether growth is ahead of or behind the fitted trajectory.

ExplanationThe residual compares measured biomass with the forecast at the same horizon. Repeated residuals in one direction indicate a persistent departure from the expected trajectory.

Independent longitudinal datasets

HydroGrowNet follows three 30-day Batavia lettuce cycles with daily images, pH, EC and water temperature. A second multi-sensor dataset follows 45 plants over 42 days under three nitrogen concentrations and two irrigation rates, with RGB, 3D, multispectral, SPAD and fluorescence records. These datasets add camera, cultivar and treatment variation that is absent from the 18-plant forecast benchmark.

Cultivar rule

Closed-soilless lettuce research also shows that genotype and macrocation supply interact in shaping the bioactive profile. This supports factorial crop-by-nutrient experiments rather than a universal nutrient rule.

Lettuce responses are strongly cultivar-dependent. Every trial names the cultivar and does not combine cultivars as interchangeable replicates.

LET-PH-001

ParameterDesign
pH levels5.5, 6.0 and 6.5
EC/formulationfixed across pH treatments
Primary outcomefresh/dry mass or a predefined physiological endpoint
Secondary outcomestissue minerals, colour, phenolics and sensory bitterness
Literature basis tested pH 5.0–6.5; separates pH and alkalinity

LET-EC-001

Use a named cultivar and treatment strengths derived from or rather than a universal 1.2–1.6 mS/cm statement. In , growth response differed between the tested lettuce and basil cultivars; showed functional-metabolite responses were genotype-dependent.

LET-FLV-001

A confirmatory experiment can test the combined pre-harvest nitrogen limitation and controlled-light treatment reported by . Primary outcomes should include sensory sweetness/bitterness and the chemical variables used in the source study.

LET-RTZ-001

Root-zone temperature is explicitly controlled because found cultivar-dependent effects on growth and °Brix. °Brix is reported as an instrumental endpoint, not automatically as perceived sweetness.

Lettuce response to root-zone temperature

Shoot fresh mass and soluble solids use separately labelled axes.

Shoot fresh mass (g) Soluble solids (°Brix) 10095908580 6.05.55.04.54.0 18.3 °C 21.1 °C Ambient shoot fresh mass soluble solids
Values
SeriesValueNote
18.3 °C treatmentShoot fresh mass 86.8 g · soluble solids 5.7 °BrixRoot fresh mass 22.7 g; shoot dry mass 5.2 g; root dry mass 0.8 g.
21.1 °C treatmentShoot fresh mass 96.8 g · soluble solids 4.5 °BrixRoot fresh mass 26.8 g; shoot dry mass 5.9 g; root dry mass 1.1 g.
Ambient treatmentShoot fresh mass 84.1 g · soluble solids 4.3 °BrixAmbient range 20.0–26.5 °C; root fresh mass 22.5 g; shoot dry mass 5.0 g; root dry mass 0.9 g.

Thakulla et al. (2021), Horticulturae, 7(9), 321, Table 3, PDF p. 6. Values transcribed without interpolation.

Article bibliography

Sources used on this page