Accurate predictions of surface runoff and soil erosion after wildfire help land managers adopt the most suitable actions to mitigate post-fire land degradation and rehabilitation planning. The use of the Artificial Neural Networks (ANNs) is advisable as hydrological prediction tool, given their lower requirement of input information compared to the traditional hydrological models. This study proposes an ANN model, purposely prepared for forest areas of the semi-arid Mediterranean environments. The ANN hydrological prediction capability in non-burned, burned by wildfire, and burned and then treated soils has been verified at the plot scale in pine forests of South-Eastern Spain. Runoff and soil loss were much higher than non-burned soils (assumed as control), but mulch application was effective to control runoff and soil erosion in burned plots. Moreover, logging did not affect the hydrological response of these soils. The model gave very accurate runoff and erosion predictions in burned and non-burned soils as well as for all soil treatments (mulching and/or logging or not), with only one exception (that is, in the condition with the combination of treatments which gave the worst performance, burning, mulching and logging), as shown by the exceptionally high model efficiency and coefficients of determination. Although further experimental tests are needed to validate the ANN applicability to the burned forests of the semi-arid conditions and other ecosystems, the use of ANN can be suggested to landscape planners as decision support system for the integrated assessment and management of forests.

Zema, D., Lucas-Borja, M., Fotia, L., Rosaci, D., Sarnè, G., Zimbone, S. (2020). Predicting the hydrological response of a forest after wildfire and soil treatments using an Artificial Neural Network. COMPUTERS AND ELECTRONICS IN AGRICULTURE, 170(105280), 1-13 [10.1016/j.compag.2020.105280].

Predicting the hydrological response of a forest after wildfire and soil treatments using an Artificial Neural Network

Sarnè, GML;
2020

Abstract

Accurate predictions of surface runoff and soil erosion after wildfire help land managers adopt the most suitable actions to mitigate post-fire land degradation and rehabilitation planning. The use of the Artificial Neural Networks (ANNs) is advisable as hydrological prediction tool, given their lower requirement of input information compared to the traditional hydrological models. This study proposes an ANN model, purposely prepared for forest areas of the semi-arid Mediterranean environments. The ANN hydrological prediction capability in non-burned, burned by wildfire, and burned and then treated soils has been verified at the plot scale in pine forests of South-Eastern Spain. Runoff and soil loss were much higher than non-burned soils (assumed as control), but mulch application was effective to control runoff and soil erosion in burned plots. Moreover, logging did not affect the hydrological response of these soils. The model gave very accurate runoff and erosion predictions in burned and non-burned soils as well as for all soil treatments (mulching and/or logging or not), with only one exception (that is, in the condition with the combination of treatments which gave the worst performance, burning, mulching and logging), as shown by the exceptionally high model efficiency and coefficients of determination. Although further experimental tests are needed to validate the ANN applicability to the burned forests of the semi-arid conditions and other ecosystems, the use of ANN can be suggested to landscape planners as decision support system for the integrated assessment and management of forests.
Articolo in rivista - Articolo scientifico
Artificial intelligence; Erosion; Hydrological; modelling; Logging; Mulching; Surface; runoff;
English
12-feb-2020
2020
170
105280
1
13
reserved
Zema, D., Lucas-Borja, M., Fotia, L., Rosaci, D., Sarnè, G., Zimbone, S. (2020). Predicting the hydrological response of a forest after wildfire and soil treatments using an Artificial Neural Network. COMPUTERS AND ELECTRONICS IN AGRICULTURE, 170(105280), 1-13 [10.1016/j.compag.2020.105280].
File in questo prodotto:
File Dimensione Formato  
Zema_2020_CEA_predicting_editor.pdf

Solo gestori archivio

Dimensione 2.47 MB
Formato Adobe PDF
2.47 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Zema_2020_CEA_predicting_post.pdf

Solo gestori archivio

Dimensione 891.31 kB
Formato Adobe PDF
891.31 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/298971
Citazioni
  • Scopus 40
  • ???jsp.display-item.citation.isi??? 35
Social impact