Latest experimental and evaluated α-decay half-lives between 82 ⩽ Z ⩽ 118 have been used to modify two empirical formulas: (i) Horoi scaling law (2004 J. Phys. G: Nucl. Part. Phys. 30 945), and Sobiczewski formula (2005 Acta Phys. Pol. B 36 3095) by adding asymmetry dependent terms (I and I ²) and refitting of the coefficients. The results of these modified formulas are found with significant improvement while compared with other 21 formulas, and, therefore, are used to predict α-decay half-lives with more precision in the unknown superheavy region. The formula of spontaneous fission (SF) half-life proposed by Bao etal (2015 J. Phys. G: Nucl. Part. Phys. 42 085101) is further modified by using ground-state shell-plus-pairing correction taken from FRDM-2012 and using the latest experimental and evaluated SF half-lives between 82 ⩽ Z ⩽ 118. Using these modified formulas, contest between α-decay and SF is probed for the nuclei within the range 112 ⩽ Z ⩽ 118 and consequently probable half-lives and decay modes are estimated. Potential decay chains of ^286−302Og and ^287−303119 (168 ⩽ N ⩽ 184: island of stability) are analyzed which are found to be in excellent agreement with available experimental data. In addition, four different machine learning models: XGBoost, random forest, decision trees, and multilayer perceptron (MLP) neural network are used to train a predictor for α-decay and SF half-lives prediction. The prediction of decay modes using XGBoost and MLP are found to be in excellent agreement with available experimental decay modes along with our predictions obtained by the above-mentioned modified formulas.

最新的实验和评估的82 ⩽ Z ⩽ 118之间的α衰变半衰期已被用于修改两个经验公式：（i）Horoi 标度定律（2004 J. Phys. G：Nucl. Part. Phys. 30 945），和Sobiczewski 公式 (2005 Acta Phys. Pol. B 36 3095) 通过添加不对称相关项（I和I ²）并重新拟合系数。发现这些修改公式的结果与其他 21 个公式相比有显着改进，因此可用于更精确地预测未知超重区域的α衰变半衰期。鲍提出的自发裂变（SF）半衰期公式 等人(2015 J. Phys. G: Nucl. Part. Phys. 42 085101) 通过使用取自 FRDM-2012 的基态壳加配对校正并使用最新的实验和评估的 SF 半衰期在 82 ⩽ Z ⩽ 118。使用这些修改后的公式，在112 ⩽ Z ⩽ 118范围内的原子核中探测α衰变和 SF之间的竞争，从而估计可能的半衰期和衰变模式。的电位衰减链^286-302 Og和^287-303 119（168⩽ Ñ⩽ 184：稳定岛）进行了分析，发现与可用的实验数据非常吻合。此外，四种不同的机器学习模型：XGBoost、随机森林、决策树和多层感知器 (MLP) 神经网络用于训练α-衰减和 SF 半衰期预测的预测器。发现使用 XGBoost 和 MLP 的衰减模式预测与可用的实验衰减模式以及我们通过上述修改公式获得的预测非常一致。