Summary
This narrative review examines artificial neural network-based approaches for air temperature forecasting, synthesising literature from 2005–2020. The authors conclude that whilst ANN methods offer promise due to computational speed and capacity to handle non-linear problems, no consensus exists on optimal methods, and most applications demonstrate effectiveness primarily for short-term forecasting rather than extended horizons.
Regional applicability
The review is methodological and geographically agnostic. Its findings on ANN effectiveness for short-term temperature forecasting are potentially applicable to United Kingdom agricultural and water resource management contexts, though the review does not specifically evaluate UK-based applications or climate conditions.
Key measures
Performance of ANN-based forecasting models; forecasting horizons (short-term vs. longer-term); model types and architectures (RNN, LSTM)
Outcomes reported
The review evaluated artificial neural network approaches (ANN, RNN, LSTM) for air temperature forecasting across 2005–2020 literature. It assessed the viability, strengths, and limitations of these deep learning techniques for temperature prediction in agricultural and water resource management contexts.
Topic tags
Dig deeper with Pulse AI.
Pulse AI has read the whole catalogue. Ask about this record, its theme, or how the findings apply to UK farming and policy — every answer cites the underlying studies.