# Lettuce growth, forecasting and cultivation trials

Canonical HTML: https://flavorotor.com/research/lettuce
Machine-readable index: https://flavorotor.com/research/data/chapters/index.json



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

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. [R57]

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. [R57]

 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. [R57]

 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.

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. [R57]

 |
 Model | MAE | RMSE | MAPE | R²

 | Persistence | 17.20 g | 18.47 g | 24.50% | 0.8378

 | Five-day linear trend | 5.56 g | 6.86 g | 8.07% | 0.9777

 | Nested-CV ridge autoregression | 2.89 g | 3.67 g | 4.18% | 0.9936

 GRW-MAE M A E = 1 n ∑ i = 1 n ∣ y i − y ^ i ∣ \mathrm{MAE}=\frac{1}{n}\sum_{i=1}^{n}\left\lvert y_i-\hat y_i\right\rvert MAE = n 1 ​ i = 1 ∑ n ​ ∣ y i ​ − y ^ ​ i ​ ∣ Mean absolute error is the average absolute difference between measured and forecast fresh biomass. **Explanation**Mean absolute error averages the absolute distance between measured and forecast fresh biomass.

 GRW-RMSE R M S E = 1 n ∑ i = 1 n ( y i − y ^ i ) 2 \mathrm{RMSE}=\sqrt{\frac{1}{n}\sum_{i=1}^{n}\left(y_i-\hat y_i\right)^2} RMSE = n 1 ​ i = 1 ∑ n ​ ( y i ​ − y ^ ​ i ​ ) 2

 ​ Root mean squared error gives more weight to large forecast errors. **Explanation**Root 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 e t + h = y t + h − y ^ t + h e_{t+h}=y_{t+h}-\hat y_{t+h} e t + h ​ = y t + h ​ − 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.

**Explanation**The 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. [R61] [R62]

## 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. [R27]

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

## LET-PH-001

 |
 Parameter | Design

 | pH levels | 5.5, 6.0 and 6.5
 | EC/formulation | fixed across pH treatments
 | Primary outcome | fresh/dry mass or a predefined physiological endpoint
 | Secondary outcomes | tissue minerals, colour, phenolics and sensory bitterness
 | Literature basis | [R06] tested pH 5.0–6.5; [R07] separates pH and alkalinity

## LET-EC-001

Use a named cultivar and treatment strengths derived from [R08] or [R09] rather than a universal 1.2–1.6 mS/cm statement. In [R08], growth response differed between the tested lettuce and basil cultivars; [R09] showed functional-metabolite responses were genotype-dependent. [R08] [R09]

## LET-FLV-001

A confirmatory experiment can test the combined pre-harvest nitrogen limitation and controlled-light treatment reported by [R10]. Primary outcomes should include sensory sweetness/bitterness and the chemical variables used in the source study. [R10]

## LET-RTZ-001

Root-zone temperature is explicitly controlled because [R11] found cultivar-dependent effects on growth and °Brix. °Brix is reported as an instrumental endpoint, not automatically as perceived sweetness. [R11]

Thakulla et al. (2021), Horticulturae, 7(9), 321, Table 3, PDF p. 6. Values transcribed without interpolation. [R11]

## References

- [R06] Kudirka, Gediminas; Viršilė, Akvilė; Sutulienė, Rūta; Laužikė, Kristina; Samuolienė, Giedrė (2023). Precise Management of Hydroponic Nutrient Solution pH: The Effects of Minor pH Changes and MES Buffer Molarity on Lettuce Physiological Properties. *Horticulturae*. https://doi.org/10.3390/horticulturae9070837
- [R07] Anderson, T. S.; Martini, M. R.; de Villiers, D.; Timmons, M. B. (2017). Growth and Tissue Elemental Composition Response of Butterhead Lettuce (Lactuca sativa, cv. Flandria) to Hydroponic Conditions at Different pH and Alkalinity. *Horticulturae*. https://doi.org/10.3390/horticulturae3030041
- [R08] Hosseini, Hadis; Mozafari, Vahid; Roosta, Hamid Reza; Shirani, Hossein; van de Vlasakker, Paulien C. H.; Farhangi, Mohsen (2021). Nutrient Use in Vertical Farming: Optimal Electrical Conductivity of Nutrient Solution for Growth of Lettuce and Basil in Hydroponic Cultivation. *Horticulturae*. https://doi.org/10.3390/horticulturae7090283
- [R09] Senizza, Biancamaria; Zhang, Leilei; Miras-Moreno, Begoña; Righetti, Laura; Zengin, Gokhan; Ak, Gunes; Bruni, Renato; Lucini, Luigi; Sifola, Maria Isabella; El-Nakhel, Christophe; Corrado, Giandomenico; Rouphael, Youssef (2020). The Strength of the Nutrient Solution Modulates the Functional Profile of Hydroponically Grown Lettuce in a Genotype-Dependent Manner. *Foods*. https://doi.org/10.3390/foods9091156
- [R10] Yang, Xiao; Hu, Jiangtao; Wang, Zheng; Huang, Tao; Xiang, Yuting; Zhang, Li; Peng, Jie; Tomas-Barberan, Francisco A.; Yang, Qichang (2023). Pre-harvest Nitrogen Limitation and Continuous Lighting Improve the Quality and Flavor of Lettuce (Lactuca sativa L.) under Hydroponic Conditions in Greenhouse. *Journal of Agricultural and Food Chemistry*. https://doi.org/10.1021/acs.jafc.2c07420
- [R11] Thakulla, Dharti; Dunn, Bruce; Hu, Bizhen; Goad, Carla; Maness, Niels (2021). Nutrient Solution Temperature Affects Growth and °Brix Parameters of Seventeen Lettuce Cultivars Grown in an NFT Hydroponic System. *Horticulturae*. https://doi.org/10.3390/horticulturae7090321
- [R27] El-Nakhel, C. et al. (2019). The bioactive profile of lettuce produced in a closed soilless system as configured by combinatorial effects of genotype and macrocation supply composition. *Food Chemistry*. https://doi.org/10.1016/j.foodchem.2019.125713
- [R57] Karimzadeh, Sara; Ahamed, M. Shamim (2025). Lettuce Dataset with RGB Canopy Images, Biomass, Nutrient Solution, and Environmental Variables for Machine Learning Model Development. *Zenodo, Version 1*. https://doi.org/10.5281/zenodo.16912088
- [R61] Shalash, Omar; Hassan, Nayira; Métwalli, Ahmed; Elhefny, Alia (2025). HydroGrowNet of Batavia Dataset. *Mendeley Data, Version 5*. https://doi.org/10.17632/g6cm3v3wdp.5
- [R62] Rodrigues, Leandro; Terra, Francisco; Rodrigues, Pedro; Moreira, Germano; Oliveira, Francisco; Moura, Pedro; Pinheiro, Isabel; Santos, Filipe; Cunha, Mário (2026). Multi-Sensor High-Throughput Phenotyping Dataset of Hydroponic Lettuce under Variable Fertigation Conditions. *Zenodo*. https://doi.org/10.5281/zenodo.20759414