Skip to main content
Geoenvironmental Disasters

Table 5 Different probabilities expressed by the prediction model

From: Adapting sudden landslide identification product (SLIP) and detecting real-time increased precipitation (DRIP) algorithms to map rainfall-triggered landslides in Western Cameroon highlands (Central-Africa)

Probability

f(Y) ≤ 0.29

Ranges

Expression

Landslide occurrence

\( {\boldsymbol{f}}_{\left({\boldsymbol{X}}_{\mathbf{1}}\right)};{\boldsymbol{f}}_{\left({\boldsymbol{X}}_{\mathbf{2}}\right)}\boldsymbol{\le}\mathbf{0.229} \)

Exp(−(−17.34 + 20.31))/1 +  exp (−(−17.34 + 20.31))

4.88%

\( \mathbf{0.229}<{\boldsymbol{f}}_{\left({\boldsymbol{X}}_{\mathbf{1}}\right)},{\boldsymbol{f}}_{\left({\boldsymbol{X}}_{\mathbf{2}}\right)}\boldsymbol{\le}\mathbf{0.394} \)

Exp(−(−17.34 − 0.0000000013 + 0.0000000002))/(1 +  exp (−(−17.34 − 0.0000000013 + 0.0000000002)))

99.99%

\( {\boldsymbol{f}}_{\left({\boldsymbol{X}}_{\mathbf{1}}\right)},{\boldsymbol{f}}_{\left({\boldsymbol{X}}_{\mathbf{2}}\right)}\boldsymbol{\ge}\mathbf{0.394} \)

Exp(−(−17.34 + 0.0000000003 − 0.000000002))/(1 +  exp (−(−17.34 + 0.0000000003 − 0.000000002)))

99.99%

\( {\boldsymbol{f}}_{\left({\boldsymbol{X}}_{\mathbf{1}}\right)}\boldsymbol{\le}\mathbf{0.229} \),

\( \mathbf{0.229}<{\boldsymbol{f}}_{\left({\boldsymbol{X}}_{\mathbf{2}}\right)}\boldsymbol{\le}\mathbf{0.394} \)

Exp(−(−17.34 + 20.31 + 0.0000000002))/(1 +  exp (−(−17.34 + 20.31 + 0.0000000002)))

4.88%

\( {\boldsymbol{f}}_{\left({\boldsymbol{X}}_{\mathbf{1}}\right)}\boldsymbol{\le}\mathbf{0.229} \),

\( {\boldsymbol{f}}_{\left({\boldsymbol{X}}_{\mathbf{2}}\right)}>\mathbf{0.394} \)

Exp(−(−17.34 + 20.31 − 0.000000002))/(1 +  exp (−(−17.34 + 20.31 − 0.000000002)))

4.88%

\( \mathbf{0.229}<{\boldsymbol{f}}_{\left({\boldsymbol{X}}_{\mathbf{1}}\right)}\boldsymbol{\le}\mathbf{0.394} \),

\( {\boldsymbol{f}}_{\left({\boldsymbol{X}}_{\mathbf{2}}\right)}\boldsymbol{\le}\mathbf{0.229} \)

Exp(−(−17.34 + 0.0000000013))/(1 +  +  exp (−(−17.34 + 0.0000000013)))

99.99%

\( {\boldsymbol{f}}_{\left({\boldsymbol{X}}_{\mathbf{2}}\right)}\boldsymbol{\le}\mathbf{0.229} \),

\( {\boldsymbol{f}}_{\left({\boldsymbol{X}}_{\mathbf{1}}\right)}>\mathbf{0.394} \)

Exp(−(−17.338 + 0.0000000002))/(1 +  exp (−(−17.338 + 0.0000000002)))

99.99%

\( \mathbf{0.229}<{\boldsymbol{f}}_{\left({\boldsymbol{X}}_{\mathbf{1}}\right)}\boldsymbol{\le}\mathbf{0.394} \),

\( {\boldsymbol{f}}_{\left({\boldsymbol{X}}_{\mathbf{2}}\right)}>\mathbf{0.394} \)

Exp(−(−17.34 − 0.0000000013 + 0.000000002))/(1 +  exp (−(−17.34 − 0.0000000013 + 0.000000002)))

99.99%

\( \mathbf{0.229}<{\boldsymbol{f}}_{\left({\boldsymbol{X}}_{\mathbf{2}}\right)}\boldsymbol{\le}\mathbf{0.394} \),

\( {\boldsymbol{f}}_{\left({\boldsymbol{X}}_{\mathbf{1}}\right)}>\mathbf{0.394} \)

Exp(−(−17.34 + 0.0000000002 + 0.00000000035))/(1 +  exp (−(−17.34 + 0.0000000002 + 0.00000000035)))

99.99%

Back to article page