Irrigation

"The controlled application of water to arable lands to supply crop water requirements not satised by rainfall." (Virginia Polytechnic Institute and State University, n.y.)
 

Sources

Virginia Polytechnic Institute and State University. "A Glossary  of Water-Related Terms", by Brian Benham. Publication 442-759
 

Related Content

Article

Mapping and Monitoring Irrigated Agriculture from Space

Irrigation illustrates a major dilemma of agriculture: On the one hand, a growing world population demands more food and biomass (for example for energy production). On the other hand, natural resources such as water are only available in limited quantities and excessive use often leads to the degradation of ecosystems, which in turn has adverse effects on agricultural production and local livelihoods.

Capacity Building and Training Material

Water Productivity and Water Accounting using WaPOR

Water Productivity and Water Accounting using WaPOR (the portal to monitor Water Productivity through Open-access of Remotely sensed derived data) is an open online course targeting practitioners and academicians who are working in water resources management and related fields and have interest in applying open access remote sensing data and other open data to assess the water resources situation and water productivity and the extent to which water productivity increases have an effect on different water users in a river basin context.

Irrigation Estimates from Remote Sensing and Land Surface Modelling

Irrigation is the most impacting anthropogenic activity on the hydrological cycle.
Despite this, the knowledge of irrigated areas and the amounts of water used for such purpose is limited.

Models and remote sensing technologies proved to be useful tools for monitoring irrigation dynamics.

This presentation provides a comparison between two different approaches (one satellite-based and one model-based) aimed at estimating irrigation quantities developed within the European Space Agency (ESA) Irrigation+ project.

Event

Local Perspectives Case Studies

Stakeholder

Govind Ballabh Pant University of Agriculture and Technology Pantnagar

G. B. Pant University of Agriculture and Technology, also known as Pantnagar University, is the first agricultural university in India. The University lies in the campus town of Pantnagar in Kichha Tehseel and in the district of Udham Singh Nagar, Uttarakhand. The university is regarded as the harbinger of the Green Revolution in India. Pantnagar University is regarded as a significant force in the development and transfer of High Yielding Variety of seeds and related technology.

Person

Space-based Solution

Addressed challenge(s)

Data-driven irrigation demand forecasting for rotational water management under the Warabandi system

Collaborating actors (stakeholders, professionals, young professionals or Indigenous voices)
Suggested solution

The proposed solution leverages Earth Observation (EO) and climate data to develop a machine learning-based irrigation demand forecasting system tailored for smallholder farmers operating under the Warabandi system. In regions where rotational irrigation governs water distribution, farmers often lack accurate tools to forecast short-term irrigation needs, leading to overuse or underuse of water, both of which impact productivity and efficiency. This space-based solution addresses the challenge by integrating EO-derived variables such as Normalized Difference Vegetation Index (NDVI), Soil-Adjusted Vegetation Index (SAVI), Land Surface Temperature (LST), and net radiation to estimate actual crop water requirements. The model enables data-driven decision-making for farmers and water managers, promoting more efficient and timely irrigation practices within fixed rotation systems.

Donor: Water Resource Accountability in Pakistan (WRAP), supported by the Foreign, Commonwealth & Development Office (FCDO)

Government Departments Involved: On-Farm Water Management (OFWM), Agriculture Department and Irrigation Department, Punjab

Community and Sectoral Engagement: Farmers’ associations and local water user groups, experts in water demand management from academia and the private sector

Inclusive Participation: Integrating voices from underrepresented communities, including women and Indigenous stakeholders.

Requirements

Data

  • Landsat time series 
  • PlanetScope time series 
  • Climate data: ERA5 (Copernicus), Flux Tower System (for validation)
  • Crop calendar and landcover data integrated with ML models

Software

Physical

  • Validation of land cover features, historical crop water use, and weather parameters through ground-based systems such as flux tower, along with crop information verified using crop calendars and spectral signatures collected from the field. 
  • The information regarding soil moisture will be verified through Soil moisture sensors.

Outline steps for a solution

  1. Data collection and sourcing (Completed)
  2. Workflow development and EO dataset integration (In progress)
  3. Data loader development and ML model setup (Completed)
  4. Training and initial testing of ML models (Completed)
  5. Automation of input data prediction via GEE/Colab (To do)
  6. Continuous irrigation forecast generation and output delivery (To do)

Steps to a solution

The solution workflow begins by collecting and preprocessing key spectral indices derived from historical satellite datasets. These include Normalized Difference Vegetation Index (NDVI), Soil-Adjusted Vegetation Index (SAVI), Land Surface Temperature (LST), Land Use Land Cover (LULC), and Net Radiation (Rn) data. This includes the:

  1. Dataset Preparation:
  • Extract temporal identifiers from each dataset.
  • Group datasets by matching dates across all indices and the target variable Evapotranspiration (ET).
  • Data pre-processing to clean datasets to remove NaN values and outliers for consistent temporal-spatial alignment.

 

  1. Model Development:
  • Features are stacked into multi-channel tensors for CNN models (e.g., 5 input channels for NDVI, SAVI, LST, Rn, and LULC).
  • For Random Forest models, the same data is flattened into tabular format with each pixel representing a row.

 

  1. Convolutional Neural Network (CNN):
  • A deep CNN model is trained with 5 layers including convolution (Conv2D) and Batch Normalization, activated using ReLU functions.
  • The final layer outputs a single channel of predicted Evapotranspiration (crop water requirement) for each crop pixel by pixel.

 

  1. Random Forest Ensemble:
  • A bootstrapped ensemble of Random Forest regressors is trained on flattened data.
  • Each model votes on ET prediction, and the final output is an average of these predictions

 

Results

Initial model testing achieved accurate crop water requirement estimation using CNN and ML. Results indicated high R² values (e.g., NDVI = 0.81, SAVI = 0.81, Net Radiation = 0.83, LST = 0.78). A 7-day irrigation forecast was generated for rice, providing actionable advisories. The model testing phase has been completed and is now in the process of being brought into a continuous irrigation advisory system to generate crop driven irrigation forecasts.

The irrigation demand forecasting model was validated across two cropping seasons with Kharif (June 2024) and Rabi (February 2024), using observed evapotranspiration (ET) from PySEBAL and flux tower data. During the Kharif season, CNN predictions closely aligned with observed ET for rice (CNN: 6.798 mm/day vs. PySEBAL: 6.370 mm/day; Flux Tower: 6.99 mm/day), while RF and XGB models showed moderate underestimations.

Similarly, in the Rabi season, wheat ET prediction by CNN (2.041 mm/day) was close to the flux tower estimate (1.86 mm/day), with XGB and RF providing slightly conservative outputs. Across both seasons, CNN consistently performed better in spatial alignment and magnitude, demonstrating its robustness in capturing seasonal irrigation demand variations across diverse crops like maize, potato, guava, and citrus orchards.

Related space-based solutions
Keywords (for the solution)
Climate Zone (addressed by the solution)
Habitat (addressed by the solution)
Region/Country (the solution was designed for, if any)
Relevant SDGs