| 1. |
- Pham, Binh Thai, et al.
(författare)
-
Performance Evaluation of Machine Learning Methods for Forest Fire Modeling and Prediction
- 2020
-
Ingår i: Symmetry. - Switzerland : MDPI. - 2073-8994. ; 12:6
-
Tidskriftsartikel (refereegranskat)abstract
- Predicting and mapping fire susceptibility is a top research priority in fire-prone forests worldwide. This study evaluates the abilities of the Bayes Network (BN), Naïve Bayes (NB), Decision Tree (DT), and Multivariate Logistic Regression (MLP) machine learning methods for the prediction and mapping fire susceptibility across the Pu Mat National Park, Nghe An Province, Vietnam. The modeling methodology was formulated based on processing the information from the 57 historical fires and a set of nine spatially explicit explanatory variables, namely elevation, slope degree, aspect, average annual temperate, drought index, river density, land cover, and distance from roads and residential areas. Using the area under the receiver operating characteristic curve (AUC) and seven other performance metrics, the models were validated in terms of their abilities to elucidate the general fire behaviors in the Pu Mat National Park and to predict future fires. Despite a few differences between the AUC values, the BN model with an AUC value of 0.96 was dominant over the other models in predicting future fires. The second best was the DT model (AUC = 0.94), followed by the NB (AUC = 0.939), and MLR (AUC = 0.937) models. Our robust analysis demonstrated that these models are sufficiently robust in response to the training and validation datasets change. Further, the results revealed that moderate to high levels of fire susceptibilities are associated with ~19% of the Pu Mat National Park where human activities are numerous. This study and the resultant susceptibility maps provide a basis for developing more efficient fire-fighting strategies and reorganizing policies in favor of sustainable management of forest resources.
|
|
| 2. |
- Pham, Binh Thai, et al.
(författare)
-
A Comparative Study of Kernel Logistic Regression, Radial Basis Function Classifier, Multinomial Naïve Bayes, and Logistic Model Tree for Flash Flood Susceptibility Mapping
- 2020
-
Ingår i: Water. - Switzerland : MDPI. - 2073-4441. ; 12:1, s. 1-21
-
Tidskriftsartikel (refereegranskat)abstract
- Risk of flash floods is currently an important problem in many parts of Vietnam. In this study, we used four machine-learning methods, namely Kernel Logistic Regression (KLR), Radial Basis Function Classifier (RBFC), Multinomial Naïve Bayes (NBM), and Logistic Model Tree (LMT) to generate flash flood susceptibility maps at the minor part of Nghe An province of the Center region (Vietnam) where recurrent flood problems are being experienced. Performance of these four methods was evaluated to select the best method for flash flood susceptibility mapping. In the model studies, ten flash flood conditioning factors, namely soil, slope, curvature, river density, flow direction, distance from rivers, elevation, aspect, land use, and geology, were chosen based on topography and geo-environmental conditions of the site. For the validation of models, the area under Receiver Operating Characteristic (ROC), Area Under Curve (AUC), and various statistical indices were used. The results indicated that performance of all the models is good for generating flash flood susceptibility maps (AUC = 0.983–0.988). However, performance of LMT model is the best among the four methods (LMT: AUC = 0.988; KLR: AUC = 0.985; RBFC: AUC = 0.984; and NBM: AUC = 0.983). The present study would be useful for the construction of accurate flash flood susceptibility maps with the objectives of identifying flood-susceptible areas/zones for proper flash flood risk management.
|
|
| 3. |
- Prakash, Om, et al.
(författare)
-
How Rigidity and Conjugation of Bidentate Ligands Affect the Geometry and Photophysics of Iron N-Heterocyclic Complexes : A Comparative Study
- 2024
-
Ingår i: Inorganic Chemistry. - : American Chemical Society (ACS). - 0020-1669 .- 1520-510X. ; 63:10, s. 4461-4473
-
Tidskriftsartikel (refereegranskat)abstract
- Two iron complexes featuring the bidentate, nonconjugated N-heterocyclic carbene (NHC) 1,1′-methylenebis(3-methylimidazol-2-ylidene) (mbmi) ligand, where the two NHC moieties are separated by a methylene bridge, have been synthesized to exploit the combined influence of geometric and electronic effects on the ground- and excited-state properties of homoleptic FeIII-hexa-NHC [Fe(mbmi)3](PF6)3 and heteroleptic FeII-tetra-NHC [Fe(mbmi)2(bpy)](PF6)2 (bpy = 2,2′-bipyridine) complexes. They are compared to the reported FeIII-hexa-NHC [Fe(btz)3](PF6)3 and FeII-tetra-NHC [Fe(btz)2(bpy)](PF6)2 complexes containing the conjugated, bidentate mesoionic NHC ligand 3,3′-dimethyl-1,1′-bis(p-tolyl)-4,4′-bis(1,2,3-triazol-5-ylidene) (btz). The observed geometries of [Fe(mbmi)3](PF6)3 and [Fe(mbmi)2(bpy)](PF6)2 are evaluated through L-Fe-L bond angles and ligand planarity and compared to those of [Fe(btz)3](PF6)3 and [Fe(btz)2(bpy)](PF6)2. The FeII/FeIII redox couples of [Fe(mbmi)3](PF6)3 (−0.38 V) and [Fe(mbmi)2(bpy)](PF6)2 (−0.057 V, both vs Fc+/0) are less reducing than [Fe(btz)3](PF6)3 and [Fe(btz)2(bpy)](PF6)2. The two complexes show intense absorption bands in the visible region: [Fe(mbmi)3](PF6)3 at 502 nm (ligand-to-metal charge transfer, 2LMCT) and [Fe(mbmi)2(bpy)](PF6)2 at 410 and 616 nm (metal-to-ligand charge transfer, 3MLCT). Lifetimes of 57.3 ps (2LMCT) for [Fe(mbmi)3](PF6)3 and 7.6 ps (3MLCT) for [Fe(mbmi)2(bpy)](PF6)2 were probed and are somewhat shorter than those for [Fe(btz)3](PF6)3 and [Fe(btz)2(bpy)](PF6)2. [Fe(mbmi)3](PF6)3 exhibits photoluminescence at 686 nm (2LMCT) in acetonitrile at room temperature with a quantum yield of (1.2 ± 0.1) × 10-4, compared to (3 ± 0.5)
|
|
| 4. |
- Prakash, Om, et al.
(författare)
-
Tailoring the Photophysical Properties of a Homoleptic Iron(II) Tetra N-Heterocyclic Carbene Complex by Attaching an Imidazolium Group to the (C∧N∧C) Pincer Ligand─A Comparative Study
- 2024
-
Ingår i: Inorganic Chemistry. - : American Chemical Society (ACS). - 0020-1669 .- 1520-510X. ; 63:6, s. 2909-2918
-
Tidskriftsartikel (refereegranskat)abstract
- We here report the synthesis of the homoleptic iron(II) N-heterocyclic carbene (NHC) complex [Fe(miHpbmi)2](PF6)4 (miHpbmi = 4-((3-methyl-1H-imidazolium-1-yl)pyridine-2,6-diyl)bis(3-methylimidazol-2-ylidene)) and its electrochemical and photophysical properties. The introduction of the π-electron-withdrawing 3-methyl-1H-imidazol-3-ium-1-yl group into the NHC ligand framework resulted in stabilization of the metal-to-ligand charge transfer (MLCT) state and destabilization of the metal-centered (MC) states. This resulted in an improved excited-state lifetime of 16 ps compared to the 9 ps for the unsubstituted parent compound [Fe(pbmi)2](PF6)2 (pbmi = (pyridine-2,6-diyl)bis(3-methylimidazol-2-ylidene)) as well as a stronger MLCT absorption band extending more toward the red spectral region. However, compared to the carboxylic acid derivative [Fe(cpbmi)2](PF6)2 (cpbmi = 1,1′-(4-carboxypyridine-2,6-diyl)bis(3-methylimidazol-2-ylidene)), the excited-state lifetime of [Fe(miHpbmi)2](PF6)4 is the same, but both the extinction and the red shift are more pronounced for the former. Hence, this makes [Fe(miHpbmi)2](PF6)4 a promising pH-insensitive analogue of [Fe(cpbmi)2](PF6)2. Finally, the excited-state dynamics of the title compound [Fe(miHpbmi)2](PF6)4 was investigated in solvents with different viscosities, however, showing very little dependency of the depopulation of the excited states on the properties of the solvent used.
|
|
