Mechanistic models are considerably more robust as predictive tools than are purely empirical models . 機械模型作為預(yù)測工具,比純粹的經(jīng)驗?zāi)P鸵晟频枚唷?i class="labawb" onClick="playMp3('sound_c_1')">
An artificial neural network ( ann ) model was developed and used in different water bodies to predict timing for environmental changes as well as for the dynamics of resources . the results show that the ann model is superior to classical statistical models ( csm ) and can be used as predictive tool for highly non - linear phenomena 用人工神經(jīng)網(wǎng)絡(luò)方法對不同水域、不同環(huán)境因子之間非線性和不確定性的復(fù)雜關(guān)系進行學(xué)習(xí)訓(xùn)練并預(yù)測檢驗,結(jié)果表明:人工神經(jīng)網(wǎng)絡(luò)方法在模擬和預(yù)測方面均優(yōu)于傳統(tǒng)的統(tǒng)計回歸模型,在資源與環(huán)境方面的應(yīng)用是可行的,具有較強的模擬預(yù)測能力。